© 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. 1700
    Prev
    Next
    INDEX
    Explanations

    phrases related to seeking something or someone specifically

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "looked after" and variations related to care or attention given to someone or something

    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
    eto
    -0.81
    ASE
    -0.80
    respective
    -0.79
    aez
    -0.76
    uten
    -0.72
    ements
    -0.71
    cci
    -0.70
    ASED
    -0.66
    cin
    -0.66
    odiac
    -0.66
    POSITIVE LOGITS
    noon
    0.97
    market
    0.87
    wards
    0.76
    word
    0.73
    math
    0.71
     midnight
    0.66
     gif
    0.64
     lunch
    0.63
    life
    0.63
    lain
    0.63
    Activations Density 0.062%

    No Known Activations