© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    6. 2207
    Prev
    Next
    INDEX
    Explanations

    references to the concept of 'inner'

    oai_token-act-pair · gpt-3.5-turbo

    references to "inner" aspects or entities, particularly related to inner cities and inner workings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KR
    -0.81
    essors
    -0.72
    HAHAHAHA
    -0.71
    KA
    -0.71
    USE
    -0.71
    LER
    -0.71
    KY
    -0.70
    DK
    -0.70
    apo
    -0.69
    KO
    -0.69
    POSITIVE LOGITS
     workings
    1.19
     inner
    1.16
     Inner
    1.00
     circumference
    0.82
    circle
    0.79
    neath
    0.78
    borough
    0.78
    most
    0.78
    ranean
    0.77
     outer
    0.77
    Activations Density 0.005%

    No Known Activations