© 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. 4-RES-JB
    11. 12
    Prev
    Next
    INDEX
    Explanations

    phrases associated with song titles

    oai_token-act-pair · gpt-3.5-turbo

    prominent song titles or musical references

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

    No Comments

    Negative Logits
    ÄŁ
    -0.72
     �
    -0.71
     prompting
    -0.66
     ende
    -0.65
    -0.65
     --------
    -0.63
     ----------------
    -0.63
     confir
    -0.60
     separately
    -0.60
     conduc
    -0.59
    POSITIVE LOGITS
    ")
    1.45
    ").
    1.44
    "),
    1.37
    "]
    1.30
    "—
    1.26
    .")
    1.25
    ",
    1.24
    "
    1.23
    %"
    1.22
    "?
    1.22
    Activations Density 0.232%

    No Known Activations