INDEX

Explanations

references to accountability and responsibility in actions or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

を守る

-0.44

 frente

-0.43

tal

-0.42

Tal

-0.41

ews

-0.41

styleType

-0.41

 alternative

-0.41

Replacement

-0.39

reserved

-0.39

logous

-0.38

POSITIVE LOGITS

parsedMessage

0.93

IUrlHelper

0.92

Билгалдахарш

0.87

RectangleBorder

0.86

 Influences

0.85

AndEndTag

0.84

 influence

0.82

 impetus

0.81

Efq

0.81

 myſelf

0.80

Activations Density 0.524%

references to accountability and responsibility in actions or events

No Comments

No Known Activations