© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 20157
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions in a structured context

    oai_token-act-pair · gpt-3.5-turbo

    legal and regulatory terms related to imprisonment or legal actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    prepositions after past-tense verbs

    Explanation Uploaded by User
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •contextual features
    fires on prepositions after past-tense verbs

    No Comments

    Negative Logits
     advoc
    -0.63
     challeng
    -0.61
    avorite
    -0.59
     theirs
    -0.57
     behav
    -0.56
    oppable
    -0.55
     prest
    -0.55
     relate
    -0.51
    nesday
    -0.51
    vertising
    -0.51
    POSITIVE LOGITS
     Released
    0.68
     ..........
    0.65
     ):
    0.64
     Profile
    0.64
     DISTRICT
    0.63
     largeDownload
    0.61
     Flavoring
    0.60
    ':
    0.59
     Pwr
    0.59
     Caption
    0.58
    Activations Density 0.616%

    No Known Activations