© 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. 8-RES-JB
    11. 23573
    Prev
    Next
    INDEX
    Explanations

    email addresses to contact support

    oai_token-act-pair · gpt-3.5-turbo

    references to contact information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ppelin
    -0.81
    Connector
    -0.70
    llor
    -0.70
    ctor
    -0.69
     acquitted
    -0.69
    ãĤ°
    -0.67
    ctors
    -0.65
    athing
    -0.64
    finished
    -0.62
    Palestinian
    -0.61
    POSITIVE LOGITS
     www
    1.15
     least
    1.13
     https
    0.98
     http
    0.96
    las
    0.87
    hens
    0.85
    onement
    0.78
     noon
    0.77
     [/
    0.76
    abase
    0.74
    Activations Density 0.105%

    No Known Activations