© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2-RES-JB
    11. 6920
    Prev
    Next
    INDEX
    Explanations

    content that is relevant to a specific topic or situation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "relevant" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PASS
    -0.73
    peak
    -0.72
     Breed
    -0.71
    rette
    -0.69
    anus
    -0.69
    bows
    -0.69
    rug
    -0.69
    OCK
    -0.67
    cker
    -0.67
    ©¶æ
    -0.67
    POSITIVE LOGITS
    relevant
    0.85
     pertinent
    0.82
     relevant
    0.82
     newsp
    0.81
     ingred
    0.75
     predic
    0.74
     guiActiveUn
    0.74
     contextual
    0.71
     explan
    0.70
     bystanders
    0.70
    Activations Density 0.011%

    No Known Activations