© 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. 6-RES-JB
    11. 14971
    Prev
    Next
    INDEX
    Explanations

    instructional phrases that describe a need for action or specific requirements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "need"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Democr
    -0.77
     Pill
    -0.76
     Dism
    -0.65
    ight
    -0.65
     Sounds
    -0.64
     delinqu
    -0.64
     Lowell
    -0.61
     horm
    -0.61
     Slide
    -0.60
    luaj
    -0.60
    POSITIVE LOGITS
    lessly
    1.18
    xus
    0.81
    èĢħ
    0.72
     convincing
    0.70
     accommodation
    0.67
    ACH
    0.67
     fewer
    0.66
    ache
    0.64
    ersive
    0.64
    ANG
    0.63
    Activations Density 0.043%

    No Known Activations