© 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. 4071
    Prev
    Next
    INDEX
    Explanations

    references to standardized tests and measurements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to standardized testing and programming

    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
    othal
    -0.96
    lein
    -0.89
    osaurs
    -0.86
    hand
    -0.85
    qua
    -0.84
    hoe
    -0.82
    hyde
    -0.80
    ando
    -0.76
    eland
    -0.74
    aires
    -0.74
    POSITIVE LOGITS
    ORY
    0.81
    sburgh
    0.70
    urally
    0.69
    s
    0.68
     Puzz
    0.65
    ãģŁ
    0.63
     plumbing
    0.63
    lished
    0.63
    ãĤ¨ãĥ«
    0.63
    oured
    0.60
    Activations Density 0.022%

    No Known Activations