© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 14937
    Prev
    Next
    INDEX
    Explanations

    references to gruesome or shocking topics, particularly related to rumors or scandals

    oai_token-act-pair · gpt-3.5-turbo

    references to controversial or shocking topics, particularly involving death or violence

    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
    ';
    -0.67
     Quan
    -0.60
    ':
    -0.59
    !.
    -0.58
    '';
    -0.58
     Izan
    -0.58
    :,
    -0.56
    +.
    -0.54
     Ic
    -0.54
    rition
    -0.53
    POSITIVE LOGITS
     outweigh
    0.68
    )</
    0.64
     outwe
    0.62
    ãĤµ
    0.56
    Downloadha
    0.55
    Must
    0.52
    omething
    0.52
    })
    0.52
    }}
    0.52
     })
    0.52
    Activations Density 1.347%

    No Known Activations