© 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. 859
    Prev
    Next
    INDEX
    Explanations

    words related to negative actions or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "demean" or related terms indicating demeaning actions or behaviors

    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
    WAYS
    -0.77
     Elves
    -0.68
    hetti
    -0.67
    OWS
    -0.66
     supper
    -0.65
    ORY
    -0.65
    tis
    -0.64
    TERN
    -0.63
    Numbers
    -0.63
     Abyss
    -0.62
    POSITIVE LOGITS
    agogue
    1.10
    ographically
    1.09
    onym
    1.06
    agog
    1.05
    ilit
    1.04
    ploy
    1.00
    igration
    0.99
    utation
    0.96
    ixed
    0.95
    ographer
    0.95
    Activations Density 0.010%

    No Known Activations