© 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. 1-RES-JB
    11. 8950
    Prev
    Next
    INDEX
    Explanations

    the word "permanently."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to permanence or lasting effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -1.08
    gio
    -0.82
     Flavoring
    -0.78
    sonian
    -0.75
     intentions
    -0.75
    ERAL
    -0.73
    ļéĨĴ
    -0.72
     Agents
    -0.71
     guesses
    -0.70
    ao
    -0.69
    POSITIVE LOGITS
     permanently
    1.15
     psychiat
    0.99
     destro
    0.96
     exting
    0.90
     bonded
    0.90
    locked
    0.90
     unemploy
    0.89
     wed
    0.86
     lodged
    0.86
     implanted
    0.84
    Activations Density 0.004%

    No Known Activations