Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 21613
    Prev
    Next
    INDEX
    Explanations

    websites and technical terms related to web development and programming

    oai_token-act-pair · gpt-3.5-turbo

    terms related to online resources, particularly URLs and references

    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
     Cotton
    -0.72
    RH
    -0.69
     ANG
    -0.67
     Sins
    -0.65
    ERO
    -0.65
     Andrews
    -0.64
     earthqu
    -0.63
    IME
    -0.63
    NAS
    -0.62
    WAR
    -0.62
    POSITIVE LOGITS
    _
    1.17
    @
    0.86
    wagen
    0.81
    /)
    0.76
    ensis
    0.76
    club
    0.75
    __
    0.75
    /.
    0.73
    ource
    0.72
     dot
    0.72
    Activations Density 0.182%

    No Known Activations