© 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. 20143
    Prev
    Next
    INDEX
    Explanations

    past tense verbs

    oai_token-act-pair · gpt-3.5-turbo

    actions related to closure or completion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    Not in Any Lists

    No Comments

    Negative Logits
    creation
    -0.66
    Topic
    -0.64
    omorph
    -0.62
     pled
    -0.62
     corpus
    -0.62
    alde
    -0.61
    respective
    -0.60
    til
    -0.60
    ISO
    -0.58
    _>
    -0.57
    POSITIVE LOGITS
     theirs
    1.01
     unexpectedly
    0.86
     hers
    0.81
     him
    0.71
     puberty
    0.70
     abruptly
    0.69
     them
    0.68
    iphany
    0.62
     recess
    0.62
     prematurely
    0.61
    Activations Density 0.393%

    No Known Activations