© 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. 2-RES-JB
    11. 24011
    Prev
    Next
    INDEX
    Explanations

    words related to psychological states or characteristics of individuals, particularly negative ones like cognitive dissonance, nervousness, selfishness, and hopelessness

    oai_token-act-pair · gpt-3.5-turbo

    suffixes related to psychological or emotional states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ergy
    -0.68
    umm
    -0.63
    solete
    -0.61
     lin
    -0.59
     Carb
    -0.58
    oug
    -0.57
    osh
    -0.57
     Colon
    -0.56
    imar
    -0.56
    opa
    -0.56
    POSITIVE LOGITS
    fulness
    1.00
    iness
    0.98
    ality
    0.91
    ful
    0.88
    uality
    0.88
    lessness
    0.87
    worthiness
    0.83
    ously
    0.83
     quot
    0.81
    uous
    0.81
    Activations Density 0.112%

    No Known Activations