© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 18638
    Prev
    Next
    INDEX
    Explanations

    contrasts between various emotional states and themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words related to contrasting emotions or states

    oai_token-act-pair · gpt-3.5-turbo
    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
     Cosponsors
    -0.80
    sites
    -0.79
    umerable
    -0.78
    ©¶æ¥µ
    -0.77
    ovies
    -0.76
    iguous
    -0.74
    ported
    -0.74
     Nare
    -0.72
    azines
    -0.72
    rm
    -0.70
    POSITIVE LOGITS
     indifference
    1.35
     optimism
    1.35
     humility
    1.34
     happiness
    1.31
     paranoia
    1.31
     insanity
    1.30
     betrayal
    1.29
     sadness
    1.29
     anger
    1.28
     empathy
    1.28
    Activations Density 0.428%

    No Known Activations