© 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. 3-RES-JB
    11. 12178
    Prev
    Next
    INDEX
    Explanations

    terms related to adrenaline and dopamine

    oai_token-act-pair · gpt-3.5-turbo

    terms related to adrenaline and its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    people
    -0.76
    nants
    -0.74
    ħ
    -0.70
    esan
    -0.70
    llan
    -0.69
     Eag
    -0.66
     Practices
    -0.65
    soever
    -0.65
    small
    -0.65
    ettlement
    -0.63
    POSITIVE LOGITS
     adrenaline
    1.20
    aline
    1.10
     exhilar
    0.98
    ulic
    0.93
     thrill
    0.84
     rush
    0.83
     fren
    0.75
     pumping
    0.74
     excitement
    0.73
     adren
    0.72
    Activations Density 0.030%

    No Known Activations