© 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. 20008
    Prev
    Next
    INDEX
    Explanations

    words related to negative trends or decreases

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "declining" and its synonyms

    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
    auts
    -0.69
     Beaut
    -0.68
    !/
    -0.65
    itect
    -0.65
    afe
    -0.65
    lette
    -0.65
    !:
    -0.65
    EXT
    -0.64
    MU
    -0.63
    omen
    -0.63
    POSITIVE LOGITS
     declining
    3.53
     declines
    2.25
     decline
    2.18
     dwindling
    2.01
     waning
    1.90
     declined
    1.79
     decreasing
    1.79
     diminishing
    1.77
     shrinking
    1.68
     deteriorating
    1.59
    Activations Density 0.015%

    No Known Activations