© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 3640
    Prev
    Next
    INDEX
    Explanations

    adjectives or verbs related to conditions of undress or discomfort

    oai_token-act-pair · gpt-3.5-turbo

    prefixes related to "under-" concepts, particularly negative or diminished states

    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
    ppo
    -0.87
    å§«
    -0.82
    gdala
    -0.81
    azines
    -0.79
    anwhile
    -0.77
    azine
    -0.76
    llan
    -0.75
    zzo
    -0.75
    bley
    -0.74
    ongyang
    -0.73
    POSITIVE LOGITS
    iscovered
    1.00
    oubt
    0.99
    etermined
    0.98
    aunted
    0.96
    irect
    0.89
    ried
    0.88
    oubtedly
    0.87
    amed
    0.86
    ifferent
    0.86
    ploy
    0.86
    Activations Density 0.015%

    No Known Activations