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. 4-RES-JB
    6. 21063
    Prev
    Next
    INDEX
    Explanations

    mentions of advertisements or marketing content

    oai_token-act-pair · gpt-3.5-turbo

    references to advertisements or ads

    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
    uckle
    -0.84
    ĨĴ
    -0.75
     Caribbean
    -0.71
    quartered
    -0.71
    20439
    -0.70
    theless
    -0.69
    Jr
    -0.68
    GoldMagikarp
    -0.67
     Cyprus
    -0.64
     Citation
    -0.64
    POSITIVE LOGITS
    vertising
    1.15
    elaide
    1.10
     hoc
    1.07
    verts
    1.06
    verb
    1.04
    ieu
    1.03
    roit
    1.03
    vertis
    1.02
    idas
    1.01
     nause
    1.01
    Activations Density 0.017%

    No Known Activations