© 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. 7-RES-JB
    11. 11805
    Prev
    Next
    INDEX
    Explanations

    may indicate uncertainty or conditionality in a statement

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases and hypothetical scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    angu
    -0.68
    enei
    -0.67
     STORY
    -0.67
     Dracula
    -0.65
    igans
    -0.64
    anz
    -0.61
     Kirin
    -0.61
     Chem
    -0.61
    igan
    -0.61
    ador
    -0.60
    POSITIVE LOGITS
    ensibly
    0.73
     nutshell
    0.71
     comprising
    0.68
    channelAvailability
    0.66
     bearer
    0.65
     mediated
    0.65
    nown
    0.64
    withstanding
    0.64
     termed
    0.64
     construed
    0.64
    Activations Density 0.230%

    No Known Activations