© 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. 1-RES-JB
    11. 9379
    Prev
    Next
    INDEX
    Explanations

    words related to computer security and software vulnerabilities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to citizenship and citizenship status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arter
    -0.69
     tyrann
    -0.66
     agony
    -0.66
     combustion
    -0.65
     deliber
    -0.65
     ramp
    -0.64
     vain
    -0.63
     deliberations
    -0.62
     gulf
    -0.62
     decom
    -0.60
    POSITIVE LOGITS
    itsch
    1.05
    epad
    0.94
    es
    0.88
    idas
    0.84
    imus
    0.84
    aunder
    0.81
    ~~~~
    0.80
    inator
    0.79
    itiz
    0.78
    eez
    0.78
    Activations Density 0.023%

    No Known Activations