Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 2649
    Prev
    Next
    INDEX
    Explanations

    phrases expressing negation or absence

    oai_token-act-pair · gpt-3.5-turbo

    assertions of absence or negation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ott
    -0.75
     Appears
    -0.71
    rn
    -0.66
    gnu
    -0.65
    leaning
    -0.64
    lish
    -0.64
    Thom
    -0.64
    aly
    -0.63
    gary
    -0.63
    elli
    -0.63
    POSITIVE LOGITS
     doubt
    1.00
    xious
    0.99
     indication
    0.98
     longer
    0.89
     detectable
    0.89
     conceivable
    0.88
     shortage
    0.88
     discern
    0.87
    oooooooooooooooo
    0.84
    oooooooo
    0.84
    Activations Density 0.044%

    No Known Activations