© 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. 12342
    Prev
    Next
    INDEX
    Explanations

    mentions of various needs, such as emotional, physical, or community needs

    oai_token-act-pair · gpt-3.5-turbo

    references to requirements or necessities within various contexts

    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
     Bom
    -0.66
     Mamm
    -0.65
    pret
    -0.64
    é¾
    -0.63
     Zam
    -0.63
    âĸ¬
    -0.61
     Rice
    -0.61
    ws
    -0.60
     Democr
    -0.60
     Polo
    -0.60
    POSITIVE LOGITS
    lessly
    1.07
    iest
    0.87
    cale
    0.84
    ful
    0.83
    lest
    0.78
    igslist
    0.77
    ache
    0.74
    iness
    0.73
    onies
    0.72
    INESS
    0.71
    Activations Density 0.049%

    No Known Activations