© 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. 14857
    Prev
    Next
    INDEX
    Explanations

    words related to data handling and analysis

    oai_token-act-pair · gpt-3.5-turbo

    terms related to requests, responses, and performance metrics in communication or data processing contexts

    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
    ALLY
    -0.89
    atalie
    -0.81
    ESA
    -0.70
     Flavoring
    -0.68
    Brother
    -0.67
    Stud
    -0.67
    Reviewer
    -0.66
    çīĪ
    -0.64
     unity
    -0.61
    ally
    -0.61
    POSITIVE LOGITS
    peed
    1.25
    pread
    1.22
    pace
    1.19
    mith
    1.15
    paces
    1.13
    ynthesis
    1.06
    linger
    1.05
    hip
    1.05
    pring
    1.04
    ource
    1.03
    Activations Density 0.428%

    No Known Activations