© 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. 8-RES-JB
    11. 4577
    Prev
    Next
    INDEX
    Explanations

    verbs or phrases indicating causation or resulting effects

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express causation or effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thia
    -0.82
    ban
    -0.66
    rina
    -0.63
    CLOSE
    -0.60
    pac
    -0.59
    phrine
    -0.59
     scrimmage
    -0.58
     champ
    -0.58
     presided
    -0.58
     withd
    -0.58
    POSITIVE LOGITS
    hift
    1.14
     sense
    1.00
     sure
    0.99
     landfall
    0.84
     Sense
    0.81
     headlines
    0.81
     matters
    0.78
     AMERICA
    0.71
    arnaev
    0.70
    URE
    0.67
    Activations Density 0.115%

    No Known Activations