© 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. 2-RES-JB
    11. 9264
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to the concept of 'golden'

    oai_token-act-pair · gpt-3.5-turbo

    the occurrences of the substring "en" in words

    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
     hitch
    -0.62
     includ
    -0.61
     loudspe
    -0.61
     Rica
    -0.60
     IPM
    -0.60
     Osc
    -0.59
    enhagen
    -0.59
     shake
    -0.59
     affirmative
    -0.58
    milo
    -0.58
    POSITIVE LOGITS
    esis
    1.10
    emies
    1.09
    chant
    1.08
    wald
    1.03
    riched
    1.01
    ema
    0.97
    igmatic
    0.95
    zel
    0.92
    berger
    0.91
    forced
    0.91
    Activations Density 0.025%

    No Known Activations