© 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. 6-RES-JB
    11. 3655
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by verbs

    oai_token-act-pair · gpt-3.5-turbo

    the preposition 'for' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ¥µ
    -0.68
    Enlarge
    -0.64
    Rocket
    -0.63
    Publisher
    -0.58
    Laun
    -0.57
    externalActionCode
    -0.56
    OTA
    -0.55
    natureconservancy
    -0.55
    SEE
    -0.54
    Reports
    -0.53
    POSITIVE LOGITS
     different
    0.62
     anything
    0.60
    arching
    0.59
     anyway
    0.59
    ardless
    0.58
     either
    0.57
     itself
    0.57
    rosso
    0.56
    anything
    0.56
     instance
    0.56
    Activations Density 0.753%

    No Known Activations