© 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. 20313
    Prev
    Next
    INDEX
    Explanations

    terms related to criminal offenses, particularly sexual assault and harassment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sexual assault and violence

    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
    mosp
    -0.85
    stanbul
    -0.85
    angular
    -0.82
    SN
    -0.81
    çĦ
    -0.79
    imum
    -0.77
    Econom
    -0.76
    flex
    -0.74
    wei
    -0.74
    cit
    -0.74
    POSITIVE LOGITS
     prevention
    1.17
     stigma
    1.09
     prosecutions
    1.07
     awareness
    1.06
     epidemic
    1.05
     Awareness
    1.04
     hotline
    1.04
     allegations
    1.03
     survivors
    1.02
     arrests
    1.02
    Activations Density 0.150%

    No Known Activations