© 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. 19695
    Prev
    Next
    INDEX
    Explanations

    specific references that start with the letter 'W' and are followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific character or letter

    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
     gratification
    -0.68
     succeeding
    -0.68
     enclosed
    -0.67
     afore
    -0.67
     Prelude
    -0.66
    arial
    -0.65
     headache
    -0.65
     bottleneck
    -0.65
     Malfoy
    -0.63
     feudal
    -0.62
    POSITIVE LOGITS
    ITNESS
    1.30
    INGS
    1.24
    ITCH
    1.22
    OW
    1.19
    OOD
    1.17
    edge
    1.16
    ipe
    1.16
    ILD
    1.14
    ORD
    1.13
    ALK
    1.13
    Activations Density 0.044%

    No Known Activations