© 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. 8-RES-JB
    11. 22565
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    subjects performing actions related to statements or claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngth
    -0.73
    geries
    -0.72
    opl
    -0.70
    antam
    -0.69
    ictional
    -0.69
    anding
    -0.66
    raints
    -0.66
     Americas
    -0.65
    ifference
    -0.65
    hang
    -0.65
    POSITIVE LOGITS
     promptly
    0.91
     vehemently
    0.90
     deem
    0.87
     duly
    0.84
     dubbed
    0.83
     gladly
    0.82
     euphem
    0.82
     dub
    0.82
     dearly
    0.81
     ironically
    0.81
    Activations Density 0.183%

    No Known Activations