INDEX

Explanations

references to consent and approval in personal or legal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Roskov

-0.63

 ſtate

-0.62

ież

-0.62

 purpoſe

-0.59

 cauſe

-0.58

 Tại

-0.58

 Unmarshal

-0.58

DockStyle

-0.57

AddTagHelper

-0.56

 ſeveral

-0.56

POSITIVE LOGITS

rrggbb

0.64

 involvement

0.61

 participation

0.61

 support

0.61

 <=",

0.59

 approval

0.59

 cooperation

0.57

participation

0.56

support

0.55

 apoyo

0.55

Activations Density 0.280%

references to consent and approval in personal or legal contexts

No Comments

No Known Activations