© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10356
    Prev
    Next
    INDEX
    Explanations

    phrases indicating authorship or attribution

    oai_token-act-pair · gpt-3.5-turbo

    possessive forms or contractions indicating ownership

    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
    olin
    -0.72
     Manufacturer
    -0.68
    ernels
    -0.66
    hered
    -0.66
    virtual
    -0.66
    wrap
    -0.65
    utenant
    -0.65
    lete
    -0.64
    winter
    -0.64
    squ
    -0.64
    POSITIVE LOGITS
     antics
    1.21
     actions
    1.19
     assertion
    1.18
     proposal
    1.18
     refusal
    1.17
     remarks
    1.17
     efforts
    1.16
     assertions
    1.16
     decision
    1.15
     plight
    1.15
    Activations Density 0.288%

    No Known Activations