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. 3-RES-JB
    6. 14519
    Prev
    Next
    INDEX
    Explanations

    words related to institutions or organizations, particularly with a suffix '-ch'

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the prefix "ch" in words

    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
     frontal
    -0.71
    berman
    -0.70
    GMT
    -0.68
     lockout
    -0.67
     Grateful
    -0.66
     comma
    -0.65
    DragonMagazine
    -0.65
     psychiat
    -0.63
     constrained
    -0.62
    ¥µ
    -0.62
    POSITIVE LOGITS
    aos
    1.23
    ampions
    1.17
    ambers
    1.10
    amps
    1.09
    amber
    1.07
    ocolate
    1.02
    amp
    1.01
    ampion
    1.00
    illing
    0.98
    inese
    0.98
    Activations Density 0.025%

    No Known Activations