© 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. 15183
    Prev
    Next
    INDEX
    Explanations

    instances where someone has reached out for contact or comment

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the word "reached."

    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
    Downloadha
    -0.80
    container
    -0.68
    cas
    -0.64
    oil
    -0.63
    ©¶æ
    -0.62
    currency
    -0.61
    nutrition
    -0.60
     demol
    -0.60
    cair
    -0.60
    PLA
    -0.59
    POSITIVE LOGITS
     Reach
    0.90
     reached
    0.88
     reach
    0.85
     fruition
    0.80
    izon
    0.72
    izen
    0.67
     stride
    0.66
    imei
    0.66
     agreement
    0.66
     consensus
    0.65
    Activations Density 0.019%

    No Known Activations