© 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. 4-RES-JB
    11. 10236
    Prev
    Next
    INDEX
    Explanations

    references to the next or future generation of products or technologies

    oai_token-act-pair · gpt-3.5-turbo

    references to different "generations" of products or technologies

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

    No Comments

    Negative Logits
    orial
    -0.75
    imon
    -0.72
    externalActionCode
    -0.70
    des
    -0.70
    iland
    -0.69
    hun
    -0.68
    mercial
    -0.68
    omo
    -0.67
    76561
    -0.67
    aleigh
    -0.66
    POSITIVE LOGITS
     iteration
    0.84
     versions
    0.80
    idable
    0.76
     onwards
    0.75
     batch
    0.74
     version
    0.74
     batches
    0.71
     onward
    0.69
     iterations
    0.69
     architectures
    0.68
    Activations Density 0.059%

    No Known Activations