© 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. 24440
    Prev
    Next
    INDEX
    Explanations

    phrases with a key word that is both common and significant for distinguishing different cases or topics

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "in which"

    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
    apult
    -0.74
    bang
    -0.72
    HQ
    -0.66
    ctor
    -0.66
    Problem
    -0.66
    rolet
    -0.66
    redit
    -0.64
    Tracker
    -0.64
    Cent
    -0.62
    swick
    -0.61
    POSITIVE LOGITS
    soever
    1.02
    upon
    0.79
     guts
    0.72
    xual
    0.72
     case
    0.71
     contrasts
    0.66
     they
    0.65
     cases
    0.64
    ases
    0.63
    adoes
    0.62
    Activations Density 0.034%

    No Known Activations