© 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. 9-RES-JB
    11. 18608
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a lack of connection or understanding with the current situation or environment

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to being out of touch or disconnected from reality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ellow
    -0.77
    arnaev
    -0.74
    ãĤ¶
    -0.73
    Ķ
    -0.70
    ucc
    -0.70
    nai
    -0.70
    sha
    -0.68
    gression
    -0.68
     Nanto
    -0.67
    eely
    -0.65
    POSITIVE LOGITS
     situations
    0.78
     altogether
    0.71
     circumstances
    0.65
     entirely
    0.65
     academ
    0.65
     mentally
    0.61
     curfew
    0.61
     anymore
    0.60
     syndrome
    0.60
     distractions
    0.60
    Activations Density 0.124%

    No Known Activations