© 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. 6-RES-JB
    6. 12148
    Prev
    Next
    INDEX
    Explanations

    words related to computer systems, IT, and technical positions such as "sys admin", "sysroots", and "operations"

    oai_token-act-pair · gpt-3.5-turbo

    specific names and terms related to technology and software systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heses
    -0.87
    roit
    -0.81
    bed
    -0.80
    olphin
    -0.78
    ality
    -0.75
    maid
    -0.74
    ricks
    -0.73
    alities
    -0.72
    ĸļ
    -0.72
    acles
    -0.70
    POSITIVE LOGITS
    È
    0.79
    =#
    0.78
    wow
    0.78
    ili
    0.74
    zzo
    0.73
    adow
    0.71
    irit
    0.69
    onder
    0.67
    ould
    0.66
    ofer
    0.65
    Activations Density 0.046%

    No Known Activations