© 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. 1476
    Prev
    Next
    INDEX
    Explanations

    words related to things being halted or postponed

    oai_token-act-pair · gpt-3.5-turbo

    terms related to delays and stoppages in processes

    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
    ocard
    -0.93
    ista
    -0.90
    avior
    -0.85
    adem
    -0.82
    istas
    -0.80
    aviour
    -0.80
    resp
    -0.75
    oise
    -0.74
    llular
    -0.73
    ructose
    -0.72
    POSITIVE LOGITS
     unresolved
    0.88
     stalled
    0.86
     backlog
    0.81
     suspense
    0.79
    ãĤ´
    0.72
     unsolved
    0.69
     shel
    0.68
    LOCK
    0.68
     Herz
    0.67
     taboo
    0.65
    Activations Density 0.019%

    No Known Activations