© 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. 14854
    Prev
    Next
    INDEX
    Explanations

    words prefixed with 'un-'

    oai_token-act-pair · gpt-3.5-turbo

    the prefix "un" indicating a negation or reversal of a concept

    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
    OPLE
    -0.83
    anwhile
    -0.79
     Dynamics
    -0.79
     briefs
    -0.77
    hetti
    -0.77
    ãĥ¼ãĥĨãĤ£
    -0.76
    jriwal
    -0.71
     Architecture
    -0.66
    phrine
    -0.65
     sinks
    -0.65
    POSITIVE LOGITS
    balanced
    1.23
    ruly
    1.21
    assuming
    1.16
    organized
    1.16
    apolog
    1.14
    cles
    1.13
    confirmed
    1.13
    leased
    1.12
    classified
    1.10
    iting
    1.09
    Activations Density 0.031%

    No Known Activations