© 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. 3956
    Prev
    Next
    INDEX
    Explanations

    town names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Town" in various contexts

    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
    terday
    -0.82
    utic
    -0.81
    aunder
    -0.78
    ibilities
    -0.75
    nces
    -0.73
    ances
    -0.73
    issance
    -0.72
    BILITY
    -0.72
    ा
    -0.71
    ossibility
    -0.71
    POSITIVE LOGITS
    ships
    1.19
    folk
    1.14
    spe
    1.07
     Halls
    1.06
    house
    1.02
    ship
    0.92
    send
    0.92
    she
    0.90
    Hall
    0.89
    houses
    0.88
    Activations Density 0.040%

    No Known Activations