© 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. 18864
    Prev
    Next
    INDEX
    Explanations

    positive adjectives related to quality, reliability, and productivity

    oai_token-act-pair · gpt-3.5-turbo

    adjectives and descriptors that convey positive or engaging qualities

    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
    é¾į
    -0.93
     Parables
    -0.79
    é¾įå
    -0.69
    ©¶æ
    -0.68
    acket
    -0.68
    osponsors
    -0.67
    eper
    -0.65
    channelAvailability
    -0.64
    Reloaded
    -0.63
    available
    -0.62
    POSITIVE LOGITS
     conservatism
    0.64
     minded
    0.63
     personalities
    0.62
    istic
    0.62
     bast
    0.61
     offspring
    0.61
     centr
    0.61
     voices
    0.60
     humour
    0.60
     compositions
    0.60
    Activations Density 0.163%

    No Known Activations