© 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. 1-RES-JB
    11. 11204
    Prev
    Next
    INDEX
    Explanations

    chemicals and hormones related to brain function and mood, such as dopamine, serotonin, testosterone, cortisol, and adrenaline

    oai_token-act-pair · gpt-3.5-turbo

    terms related to neurotransmitters and hormones affecting mood and physiological responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    places
    -0.85
    È
    -0.84
    Earth
    -0.84
     Antiqu
    -0.80
     Spaces
    -0.80
    ANGE
    -0.79
    ĪĴ
    -0.78
    atche
    -0.74
    Cos
    -0.74
    Rated
    -0.74
    POSITIVE LOGITS
    osterone
    1.14
     gland
    1.10
     adrenaline
    1.10
    phrine
    1.01
     testosterone
    1.00
     secretion
    0.98
     glands
    0.98
     dopamine
    0.98
     cortisol
    0.97
     adren
    0.95
    Activations Density 0.014%

    No Known Activations