© 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. 1-RES-JB
    6. 14090
    Prev
    Next
    INDEX
    Explanations

    phrases indicating something has been thoroughly recorded or verified

    oai_token-act-pair · gpt-3.5-turbo

    instances where something has been officially recorded or reported

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adding
    -0.86
    arma
    -0.85
    awar
    -0.84
    apa
    -0.80
    mun
    -0.79
    spr
    -0.78
    enta
    -0.76
    apo
    -0.75
    sv
    -0.75
    yss
    -0.71
    POSITIVE LOGITS
     documented
    1.09
     documenting
    0.93
    documented
    0.90
    ĸļ
    0.81
     documentation
    0.80
    IGHTS
    0.79
    ocument
    0.77
    RIPT
    0.76
     Documentation
    0.74
    urally
    0.72
    Activations Density 0.007%

    No Known Activations