INDEX

Explanations

symbols and punctuation marks that indicate structure in conversation, such as question marks, quotes, and parentheses

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Code snippets or error messages

np_acts-logits-general · gemini-2.0-flash

numbers followed by punctuation or list items

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Figure

-0.40

 Type

-0.39

 Class

-0.39

 Full

-0.38

 Himself

-0.38

 Section

-0.37

New

-0.36

ſelves

-0.35

Of

-0.34

For

-0.34

POSITIVE LOGITS

ロウィン

0.91

 חיצוניים

0.87

๬

0.83

 vooz

0.83

ſicht

0.82

ſſung

0.82

 unſer

0.82

 beſch

0.81

 verſch

0.81

majánló

0.81

Activations Density 0.411%

symbols and punctuation marks that indicate structure in conversation, such as question marks, quotes, and parentheses

Code snippets or error messages

numbers followed by punctuation or list items

No Comments

No Known Activations