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. 9-RES-JB
    6. 10171
    Prev
    Next
    INDEX
    Explanations

    legal and regulatory terms or phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to regulatory frameworks or legal conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gigs
    -0.75
    whatever
    -0.74
    eno
    -0.70
     nowhere
    -0.69
    oops
    -0.69
    oil
    -0.66
    pher
    -0.66
    img
    -0.66
    maybe
    -0.66
     hardly
    -0.66
    POSITIVE LOGITS
     foregoing
    1.55
     following
    1.25
     licensee
    1.17
     afore
    1.15
     applicant
    1.15
     remainder
    1.09
     respective
    1.08
     Commission
    1.05
     aforementioned
    1.03
     Applicant
    1.03
    Activations Density 0.544%

    No Known Activations