© 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. 15291
    Prev
    Next
    INDEX
    Explanations

    scientific research-related words and phrases

    oai_token-act-pair · gpt-3.5-turbo

    mentions of research teams and their activities

    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
    cow
    -0.69
    dos
    -0.68
     Doctrine
    -0.64
     decency
    -0.63
    swing
    -0.62
     CGI
    -0.61
    remember
    -0.60
    OPA
    -0.59
    ãĥĸ
    -0.59
    ãĥ¼ãĥĨãĤ£
    -0.58
    POSITIVE LOGITS
    heses
    0.87
     authors
    0.83
    hesis
    0.81
    authors
    0.81
    Methods
    0.80
    ĨĴ
    0.77
     uncover
    0.76
     resear
    0.75
    abbit
    0.75
    redients
    0.74
    Activations Density 0.110%

    No Known Activations