© 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. 10-RES-JB
    11. 9885
    Prev
    Next
    INDEX
    Explanations

    words related to societal attitudes and beliefs towards certain issues or behaviors

    oai_token-act-pair · gpt-3.5-turbo

    references to societal perceptions and discussions about homosexuality and related cultural attitudes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çīĪ
    -0.97
     Cosponsors
    -0.95
     Readers
    -0.86
    stanbul
    -0.80
    ullivan
    -0.80
    audi
    -0.78
     Emails
    -0.77
    ersen
    -0.76
    icion
    -0.76
    swick
    -0.76
    POSITIVE LOGITS
     innate
    1.26
     sinful
    1.21
     taboo
    1.19
     inherent
    1.18
     morally
    1.16
     pathology
    1.14
     immoral
    1.13
     punishable
    1.12
     immutable
    1.11
     shameful
    1.09
    Activations Density 0.377%

    No Known Activations