© 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. 4060
    Prev
    Next
    INDEX
    Explanations

    mentions of substances or items related to molasses

    oai_token-act-pair · gpt-3.5-turbo

    terms related to environmental and physical traits that involve "asses."

    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
     parent
    -0.63
     Iw
    -0.61
    yi
    -0.60
     threaded
    -0.59
     Wanted
    -0.58
     utility
    -0.58
     zip
    -0.56
     description
    -0.56
     tug
    -0.56
     bursting
    -0.56
    POSITIVE LOGITS
    asses
    4.77
    assed
    2.34
    assing
    2.16
    ass
    2.04
    asse
    1.85
    assy
    1.84
    ASS
    1.82
    assment
    1.18
    arse
    1.11
    assies
    1.04
    Activations Density 0.007%

    No Known Activations