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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-RES-JB
    6. 20739
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Val" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named Val

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OME
    -0.77
    pread
    -0.68
    OOL
    -0.65
     oven
    -0.64
     Ways
    -0.62
     roaming
    -0.62
     depreciation
    -0.60
     owl
    -0.60
     Owl
    -0.58
     Radical
    -0.58
    POSITIVE LOGITS
    idation
    1.45
    idated
    1.27
    uable
    1.18
    idate
    1.18
    idity
    1.18
    leys
    1.16
    ueless
    1.10
    idates
    1.08
    encia
    1.08
    entin
    1.03
    Activations Density 0.021%

    No Known Activations