© 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. 13011
    Prev
    Next
    INDEX
    Explanations

    terms related to personal qualities like charisma

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals with charismatic traits

    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
     Odyssey
    -0.89
     Wem
    -0.72
    ãĤº
    -0.71
    andom
    -0.70
    edIn
    -0.69
    GROUND
    -0.66
    atorium
    -0.65
     FANTASY
    -0.65
    quartered
    -0.64
     MER
    -0.64
    POSITIVE LOGITS
     charisma
    0.95
     Sheen
    0.90
    atform
    0.76
     charismatic
    0.73
    urst
    0.69
     Chow
    0.69
    plain
    0.69
     Cha
    0.68
    icts
    0.68
    apeake
    0.67
    Activations Density 0.040%

    No Known Activations