© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 9350
    Prev
    Next
    INDEX
    Explanations

    contractions with an apostrophe

    oai_token-act-pair · gpt-3.5-turbo

    the use of single quotation marks

    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
     Leilan
    -0.74
    avorite
    -0.74
    âĹ¼
    -0.73
    igslist
    -0.72
    nown
    -0.70
     Izan
    -0.70
     destro
    -0.70
     ..............
    -0.67
     Archdemon
    -0.66
     lapse
    -0.63
    POSITIVE LOGITS
    til
    1.20
    cause
    1.18
    Interstitial
    1.08
     ',
    1.07
    -'
    1.06
    tis
    1.05
    neath
    1.03
    Mech
    1.00
    taboola
    0.96
    no
    0.94
    Activations Density 0.034%

    No Known Activations