© 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. 3-RES-JB
    11. 6571
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or events

    oai_token-act-pair · gpt-3.5-turbo

    key actions and events occurring in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ).[
    -0.51
    ?).
    -0.49
    .).
    -0.49
    )).
    -0.48
    %).
    -0.48
    ).
    -0.44
    ]."
    -0.44
     thereto
    -0.42
    )."
    -0.41
    SPONSORED
    -0.41
    POSITIVE LOGITS
    undrum
    0.39
    ':
    0.34
    arij
    0.32
    reements
    0.31
     Gamble
    0.30
     Grassley
    0.29
     Quan
    0.29
    anmar
    0.29
    eanor
    0.29
     puzzled
    0.29
    Activations Density 8.640%

    No Known Activations