© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 2975
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software or programming

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to hazards and risks associated with food

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ŃĶ
    -0.75
     Beir
    -0.73
    ĸļ
    -0.71
    \\\\\\\\
    -0.70
    ©¶æ
    -0.66
    ĸļ士
    -0.65
    VIDIA
    -0.65
    SHARE
    -0.64
     exting
    -0.62
    ğ
    -0.62
    POSITIVE LOGITS
     RPM
    0.58
     rpm
    0.56
    outheastern
    0.54
     Air
    0.53
     Effective
    0.52
     Continuous
    0.52
     Ic
    0.51
     Protocol
    0.49
     anymore
    0.48
    ].
    0.48
    Activations Density 0.093%

    No Known Activations