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. 14199
    Prev
    Next
    INDEX
    Explanations

    legal or bureaucratic terms and application processes

    oai_token-act-pair · gpt-3.5-turbo

    references to official documentation and application procedures

    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
    zinski
    -0.79
    usterity
    -0.74
     Tarant
    -0.73
    seless
    -0.72
    ~~~~~~~~
    -0.72
     metaphors
    -0.72
    Deep
    -0.72
     cannibal
    -0.71
     Harm
    -0.70
     sacrificed
    -0.69
    POSITIVE LOGITS
     registration
    1.50
     paperwork
    1.49
     registrations
    1.46
     Registration
    1.40
     registering
    1.34
     applicants
    1.33
     filings
    1.31
     Registrar
    1.27
     applicant
    1.24
     eligibility
    1.24
    Activations Density 0.527%

    No Known Activations