© 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. 14446
    Prev
    Next
    INDEX
    Explanations

    verbs in the infinitive form

    oai_token-act-pair · gpt-3.5-turbo

    phrases that suggest solutions or instructions

    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
     looms
    -0.66
    âĿ
    -0.63
    listed
    -0.61
     Bengal
    -0.59
    chains
    -0.59
    Dur
    -0.59
     Hind
    -0.59
     handles
    -0.58
    quickShipAvailable
    -0.57
     faces
    -0.56
    POSITIVE LOGITS
     minimize
    0.98
     maximize
    0.97
     illuminate
    0.93
     provide
    0.93
     dismantle
    0.93
     enlarge
    0.92
     educate
    0.91
     confuse
    0.90
     apply
    0.89
     conserve
    0.89
    Activations Density 0.069%

    No Known Activations