© 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. 8-RES-JB
    11. 3927
    Prev
    Next
    INDEX
    Explanations

    names or words related to the emotion of sadness

    oai_token-act-pair · gpt-3.5-turbo

    expressions of sadness or sorrow

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 8 - sadness

    No Comments

    Negative Logits
     helic
    -0.72
     Expend
    -0.67
     FANT
    -0.66
    UID
    -0.66
    ouver
    -0.65
    vernment
    -0.62
    RAFT
    -0.61
    ORGE
    -0.61
    ITNESS
    -0.59
     laund
    -0.59
    POSITIVE LOGITS
    der
    1.26
    omas
    1.10
    istic
    1.09
     Pupp
    0.96
    emic
    0.91
    ifiers
    0.89
    hya
    0.88
    istically
    0.88
    hus
    0.86
    ness
    0.86
    Activations Density 0.035%

    No Known Activations