© 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. 10-RES-JB
    11. 14165
    Prev
    Next
    INDEX
    Explanations

    numbers indicating ranking or position

    oai_token-act-pair · gpt-3.5-turbo

    numeric rankings or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rador
    -0.72
    Materials
    -0.71
    etsy
    -0.69
    raught
    -0.64
    ossier
    -0.64
    IAL
    -0.62
    habi
    -0.62
    INTON
    -0.60
    hire
    -0.60
     Shroud
    -0.60
    POSITIVE LOGITS
    plates
    1.05
     crunch
    0.94
    plate
    0.92
     pad
    0.85
     plate
    0.84
     plates
    0.83
    enance
    0.82
    lessness
    0.75
     Ones
    0.73
    esses
    0.72
    Activations Density 0.045%

    No Known Activations