Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 14746
    Prev
    Next
    INDEX
    Explanations

    blunt and frank language

    oai_token-act-pair · gpt-3.5-turbo

    words associated with directness and straightforwardness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Haunted
    -0.81
    Mich
    -0.77
    ITNESS
    -0.75
    ————————————————
    -0.75
    ————————
    -0.74
    YL
    -0.74
     Occupations
    -0.73
    CF
    -0.73
    Cour
    -0.71
    SEC
    -0.71
    POSITIVE LOGITS
     blunt
    1.40
    odox
    0.93
     nodd
    0.87
     frank
    0.84
    entimes
    0.80
     skew
    0.80
     parting
    0.77
     blasts
    0.74
    ãĤ©
    0.74
     disse
    0.73
    Activations Density 0.008%

    No Known Activations