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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9-RES-JB
    6. 21468
    Prev
    Next
    INDEX
    Explanations

    actions or activities related to communication or storytelling

    oai_token-act-pair · gpt-3.5-turbo

    activities related to storytelling and performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    >]
    -0.69
     [/
    -0.67
    pox
    -0.66
    andum
    -0.65
    oola
    -0.65
     [+
    -0.65
    âĶĢâĶĢ
    -0.64
    taker
    -0.64
    osate
    -0.63
    malink
    -0.63
    POSITIVE LOGITS
     various
    1.22
     countless
    1.14
     innumerable
    1.13
     conferences
    1.11
     myriad
    1.10
     varying
    1.10
     assorted
    1.08
     assignments
    1.04
     anecdotes
    1.04
     conventions
    1.03
    Activations Density 1.300%

    No Known Activations