© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 7450
    Prev
    Next
    INDEX
    Explanations

    adjectives and nouns related to actions or attributes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to consensus, power dynamics, and social structures

    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
     looph
    -0.57
    BuyableInstoreAndOnline
    -0.55
     Sachs
    -0.52
    CAST
    -0.52
    ĻĤ
    -0.52
    rez
    -0.52
     et
    -0.52
     HuffPost
    -0.51
     Doe
    -0.51
     Uz
    -0.50
    POSITIVE LOGITS
     alike
    1.38
     versa
    1.24
     accordingly
    1.21
     thereof
    1.20
     respectively
    1.17
     thereafter
    1.06
     thereto
    0.96
     consequently
    0.95
     therein
    0.91
     importantly
    0.88
    Activations Density 0.722%

    No Known Activations