© 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. 429
    Prev
    Next
    INDEX
    Explanations

    rock music-related terms and references

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Rock" and variations thereof

    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
     siph
    -0.70
     Fa
    -0.67
     gest
    -0.66
     refugee
    -0.65
     curs
    -0.65
     ferry
    -0.64
     âĩ
    -0.64
     equival
    -0.64
     Flynn
    -0.63
    orthy
    -0.63
    POSITIVE LOGITS
    Rock
    3.97
    rock
    1.69
     Rocky
    1.53
     Rock
    1.43
     ROCK
    1.41
     Rockies
    1.21
    Roll
    1.18
    Wood
    1.18
    Bone
    1.18
    Brook
    1.17
    Activations Density 0.028%

    No Known Activations