© 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. 13189
    Prev
    Next
    INDEX
    Explanations

    phrases containing the pattern "-ing" followed by a dash and a numeral

    oai_token-act-pair · gpt-3.5-turbo

    phrases or words that indicate a downward or sliding motion

    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
    HCR
    -0.73
     âĶľ
    -0.70
     privately
    -0.63
     Maher
    -0.60
     sorts
    -0.60
     Orc
    -0.60
     scant
    -0.58
     Legislative
    -0.57
     Vaughn
    -0.57
     grizz
    -0.56
    POSITIVE LOGITS
    ups
    1.23
    forward
    1.21
    out
    1.19
    up
    1.18
    through
    1.17
    outs
    1.13
    toe
    1.08
    down
    1.05
    ahead
    1.05
    away
    1.05
    Activations Density 0.067%

    No Known Activations