INDEX

Explanations

specific combinations of letters, particularly related to a structured format, likely associated with legal or official documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

XX

-0.46

 preſent

-0.45

®:

-0.44

 Whence

-0.44

?”.

-0.43

 prise

-0.43

 ſame

-0.43

 Thing

-0.43

DX

-0.42

 anſ

-0.42

POSITIVE LOGITS

enumi

0.80

0.74

TargetException

0.73

0.72

awtextra

0.71

Sucesor

0.70

0.69

0.68

Activations Density 0.087%

specific combinations of letters, particularly related to a structured format, likely associated with legal or official documents

No Comments

No Known Activations