INDEX

Explanations

references to specific locations and time settings in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 nakalista

-0.90

IntoConstraints

-0.81

 саны

-0.80

 الرياضيه

-0.80

RenderAtEndOf

-0.75

 FetchType

-0.72

Autoritní

-0.72

 مرئيه

-0.72

 Roskov

-0.72

 insuffisamment

-0.71

POSITIVE LOGITS

 setting

0.47

glUniform

0.42

govor

0.37

Duf

0.35

ahara

0.35

helm

0.34

©

0.34

frontmatter

0.34

text

0.34

hal

0.34

Activations Density 0.267%

references to specific locations and time settings in various contexts

No Comments

No Known Activations