© 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. 7-RES-JB
    11. 6419
    Prev
    Next
    INDEX
    Explanations

    adverbs describing the intensity or certainty of a statement

    oai_token-act-pair · gpt-3.5-turbo

    words indicating emphasis or qualification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     occurs
    -0.81
    ulence
    -0.81
     arises
    -0.73
    aceutical
    -0.71
    aneers
    -0.71
     originate
    -0.69
    iox
    -0.68
    ortmund
    -0.68
     meshes
    -0.68
     derives
    -0.67
    POSITIVE LOGITS
     aware
    1.31
     thankful
    1.25
     able
    1.21
     glad
    1.16
     enjoying
    1.13
     grateful
    1.10
     fortunate
    1.09
     trying
    1.09
     proud
    1.07
     accustomed
    1.07
    Activations Density 0.289%

    No Known Activations