© 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. 2-RES-JB
    11. 1047
    Prev
    Next
    INDEX
    Explanations

    sentences containing the word 'no'

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases indicating the absence of something or lack of evidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RAFT
    -0.71
    Quote
    -0.70
    staking
    -0.69
    tein
    -0.67
    iership
    -0.67
    endar
    -0.64
    ameron
    -0.64
    Untitled
    -0.64
    ries
    -0.63
    otton
    -0.62
    POSITIVE LOGITS
    xious
    1.21
     longer
    1.03
     doubt
    0.98
     matter
    0.90
     conceivable
    0.88
    oooo
    0.87
    except
    0.86
     indication
    0.85
    oooooooooooooooo
    0.83
    oooooooo
    0.81
    Activations Density 0.091%

    No Known Activations