© 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. 0-RES-JB
    11. 2863
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "attachment"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to teaching and learning processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rave
    -0.69
     commons
    -0.66
     Rogue
    -0.66
     backlash
    -0.63
     vomiting
    -0.61
     Frey
    -0.61
     alternatives
    -0.60
     nationalism
    -0.60
     resistance
    -0.60
     airlines
    -0.59
    POSITIVE LOGITS
    ACH
    4.31
    aches
    2.12
    ached
    2.05
    ach
    1.97
    aching
    1.90
    acher
    1.79
    ache
    1.51
    achers
    1.44
    ECH
    1.40
    achable
    1.40
    Activations Density 0.007%

    No Known Activations