© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 8944
    Prev
    Next
    INDEX
    Explanations

    the word "is" occurring in sentences

    oai_token-act-pair · gpt-3.5-turbo

    repetitive use of the verb "is."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iates
    -0.65
     Telesc
    -0.62
     Commun
    -0.59
    inav
    -0.59
     peg
    -0.59
     encounters
    -0.58
    itches
    -0.57
    know
    -0.56
    ilst
    -0.55
     floats
    -0.55
    POSITIVE LOGITS
    rael
    1.18
    senal
    1.07
    cussion
    1.02
     definitely
    1.00
    nt
    1.00
     hereby
    0.96
    olation
    0.94
     supposed
    0.94
    omorph
    0.88
     indeed
    0.88
    Activations Density 0.757%

    No Known Activations