© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 2630
    Prev
    Next
    INDEX
    Explanations

    references to public statements or claims

    oai_token-act-pair · gpt-3.5-turbo

    statements or assertions related to public discourse and communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ritten
    -0.65
    ategory
    -0.63
     oneself
    -0.62
    aples
    -0.60
    everal
    -0.56
    uminati
    -0.56
     Its
    -0.55
     ILCS
    -0.55
     Shinzo
    -0.55
    ccording
    -0.54
    POSITIVE LOGITS
    ings
    0.77
     spree
    0.74
    nings
    0.69
    tracking
    0.68
    mates
    0.67
    fulness
    0.67
    naires
    0.66
     regarding
    0.65
     colleague
    0.65
    oids
    0.64
    Activations Density 0.338%

    No Known Activations