© 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. 6-RES-JB
    11. 21959
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or ethical matters

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal accusations and intentionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ?".
    -0.50
     ......
    -0.43
    +.
    -0.43
     Jackets
    -0.43
    onga
    -0.42
     killers
    -0.42
     Defenders
    -0.42
    ".
    -0.42
    ''.
    -0.42
    !".
    -0.41
    POSITIVE LOGITS
    advert
    0.47
     publicized
    0.46
    ritten
    0.46
    announced
    0.45
     archived
    0.45
    jamin
    0.44
    her
    0.44
    sided
    0.43
    evidence
    0.43
    arming
    0.43
    Activations Density 0.928%

    No Known Activations