© 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. 6-RES-JB
    11. 9869
    Prev
    Next
    INDEX
    Explanations

    adjectives conveying emotional responses like excitement, ease, toughness, wonder, terribleness, fun, and difficulty

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that convey various degrees of sentiment or opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iencies
    -0.91
    lees
    -0.90
    apons
    -0.85
    apses
    -0.82
    assies
    -0.81
    events
    -0.80
    ngth
    -0.78
    votes
    -0.76
    ptives
    -0.76
    ravings
    -0.75
    POSITIVE LOGITS
     reminder
    1.16
     thing
    1.11
     example
    1.06
     piece
    1.03
     asset
    1.03
     topic
    1.03
     proposition
    1.00
     boon
    0.98
     indication
    0.98
     source
    0.97
    Activations Density 0.255%

    No Known Activations