Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 23692
    Prev
    Next
    INDEX
    Explanations

    comparative statements describing quality or preference

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "best" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    catentry
    -0.64
    geries
    -0.60
     Hebdo
    -0.60
    ngth
    -0.59
     Emer
    -0.58
     Tide
    -0.56
     MAC
    -0.56
    cking
    -0.55
     impossibility
    -0.55
    ities
    -0.54
    POSITIVE LOGITS
     suited
    1.18
    ower
    1.14
     summed
    1.10
    ow
    1.05
    served
    1.04
    owing
    1.03
    ows
    1.02
    owed
    1.02
     served
    1.00
     avoided
    0.98
    Activations Density 0.046%

    No Known Activations