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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-RES-JB
    6. 10709
    Prev
    Next
    INDEX
    Explanations

    descriptive terms indicating quality or competence

    oai_token-act-pair · gpt-3.5-turbo

    well-structured and well-executed descriptions or evaluations of various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alos
    -1.00
    ©¶æ
    -0.80
     teasp
    -0.80
    athy
    -0.78
    umbn
    -0.71
    ubi
    -0.70
    oother
    -0.70
    è£ħ
    -0.68
    lua
    -0.68
    irlf
    -0.68
    POSITIVE LOGITS
     (>
    0.68
     notions
    0.63
     (<
    0.63
     commodity
    0.59
     Schne
    0.59
     occupations
    0.58
     international
    0.58
     Framework
    0.57
    wealth
    0.57
     friendships
    0.57
    Activations Density 0.226%

    No Known Activations