© 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. 11-RES-JB
    11. 18702
    Prev
    Next
    INDEX
    Explanations

    phrases related to signing up or subscribing

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to user registration and account status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thing
    -0.62
    Lay
    -0.61
     dens
    -0.60
     apples
    -0.59
     preach
    -0.58
    arthed
    -0.58
    arro
    -0.58
    HP
    -0.58
     priests
    -0.58
     sting
    -0.57
    POSITIVE LOGITS
     requested
    0.92
     redirected
    0.75
     logged
    0.72
     Password
    0.72
     subscribed
    0.70
     Login
    0.70
    edia
    0.68
     browser
    0.68
    igrated
    0.66
    Login
    0.65
    Activations Density 0.080%

    No Known Activations