© 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. 8-RES-JB
    11. 16828
    Prev
    Next
    INDEX
    Explanations

    terms related to records or recording

    oai_token-act-pair · gpt-3.5-turbo

    mentions of recovery or related concepts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MENTS
    -0.76
    ahime
    -0.73
    glers
    -0.62
     Nicarag
    -0.61
     NIC
    -0.60
    holes
    -0.60
    MENT
    -0.59
    furt
    -0.59
    loo
    -0.58
     flawed
    -0.58
    POSITIVE LOGITS
    ruit
    1.23
    ycle
    1.22
    urrent
    1.16
    ipient
    1.14
    ruits
    1.14
    ursive
    1.14
    ords
    1.13
    ording
    1.13
    overed
    1.10
    ipes
    1.10
    Activations Density 0.022%

    No Known Activations