INDEX

Explanations

This neuron appears to activate on a variety of structured code-like text, possibly related to specific characters or structured formatting within code or data.

oai_token-act-pair · gemini-2.0-flash

non-English words or code-related terms

np_token-act-pair-logits · gpt-4o-mini

code/foreign languages

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

EDEFAULT

-0.77

 صوتيه

-0.76

tanleria

-0.74

InitVars

-0.73

Obrázky

-0.73

WriteBarrier

-0.71

 виправивши

-0.68

TypedDataSet

-0.68

bootstrapcdn

-0.67

 niggas

-0.66

POSITIVE LOGITS

adí

0.47

 jLabel

0.46

док

0.42

 للاسماء

0.42

+#+

0.42

enumi

0.40

وض

0.40

сок

0.40

findpost

0.40

unek

0.39

Activations Density 1.214%

This neuron appears to activate on a variety of structured code-like text, possibly related to specific characters or structured formatting within code or data.

non-English words or code-related terms

code/foreign languages

No Comments

No Known Activations

This neuron appears to activate on a variety of structured code-like text, possibly related to specific characters or structured formatting within code or data.

non-English words or code-related terms

code/foreign languages

No Comments

No Known Activations