Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 8998
    Prev
    Next
    INDEX
    Explanations

    words related to research methods and psychological concepts

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to emotion regulation and its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hemp
    -0.85
    wald
    -0.84
    thur
    -0.82
     Pwr
    -0.80
    aqu
    -0.80
    eday
    -0.79
    lah
    -0.78
    wered
    -0.78
    ©¶æ¥µ
    -0.76
    ageddon
    -0.76
    POSITIVE LOGITS
     cues
    1.45
     interpersonal
    1.33
     emotion
    1.31
     motivational
    1.28
     perceptions
    1.27
     empathy
    1.27
     arousal
    1.26
     behaviors
    1.26
     emotions
    1.26
     emotional
    1.24
    Activations Density 0.641%

    No Known Activations