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. 6-RES-JB
    6. 18400
    Prev
    Next
    INDEX
    Explanations

    versions expressed in numbers, such as software or operating system versions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of decimal points or version numbers in a technical context

    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
     offic
    -0.70
     dishon
    -0.69
     deliber
    -0.68
     spectator
    -0.65
     rhy
    -0.64
     protesting
    -0.64
     indo
    -0.64
     stagnant
    -0.64
     shadowy
    -0.64
     accus
    -0.64
    POSITIVE LOGITS
    dylib
    1.15
    jar
    0.84
    fm
    0.81
    0
    0.80
    compatible
    0.80
    zip
    0.79
    jpg
    0.79
    launch
    0.79
    isSpecialOrderable
    0.78
    xxx
    0.76
    Activations Density 0.040%

    No Known Activations