© 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. 9-RES-JB
    11. 9004
    Prev
    Next
    INDEX
    Explanations

    references to events and activities happening within a specific time frame

    oai_token-act-pair · gpt-3.5-turbo

    references to television shows and viewing habits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    trak
    -0.71
    lyak
    -0.64
    CVE
    -0.60
    è¦ļéĨĴ
    -0.60
    Þ
    -0.60
    ovo
    -0.59
     voic
    -0.58
    Ĕ
    -0.58
     TheNitrome
    -0.57
     externalTo
    -0.57
    POSITIVE LOGITS
     nowadays
    0.84
     seasons
    0.77
     weekends
    0.75
     mornings
    0.72
     offseason
    0.69
     summers
    0.68
     summer
    0.67
     weekday
    0.67
    usually
    0.66
    season
    0.66
    Activations Density 0.585%

    No Known Activations