© 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. 0-RES-JB
    11. 22627
    Prev
    Next
    INDEX
    Explanations

    words related to a particular last name - "Chaffetz"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific individual named Chaffetz

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     floating
    -0.63
     isolated
    -0.62
     mature
    -0.61
     safer
    -0.59
     positive
    -0.59
     distance
    -0.59
     divers
    -0.58
     radius
    -0.58
     parent
    -0.57
     less
    -0.57
    POSITIVE LOGITS
    etz
    4.92
    atz
    1.49
    eta
    1.36
    itz
    1.36
    tz
    1.28
    icz
    1.27
    itsch
    1.11
    etts
    1.10
    eton
    1.08
    ets
    1.07
    Activations Density 0.014%

    No Known Activations