© 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. 7-RES-JB
    11. 21456
    Prev
    Next
    INDEX
    Explanations

    words related to emotions like anger, frustration, fear, and resentment

    oai_token-act-pair · gpt-3.5-turbo

    expressions of anger and related emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amins
    -0.67
    mans
    -0.66
    å¸
    -0.65
     Conduct
    -0.63
     rearr
    -0.61
    ĻĤ
    -0.60
     rough
    -0.59
    arnaev
    -0.56
     Locations
    -0.56
    Numbers
    -0.56
    POSITIVE LOGITS
    fulness
    1.07
    lessness
    1.02
    wart
    0.94
    lessly
    0.92
    fully
    0.91
    ingly
    0.90
     stricken
    0.90
     stemming
    0.87
     overcame
    0.86
    rained
    0.85
    Activations Density 0.124%

    No Known Activations