INDEX

Explanations

references to actions related to "committing" or "commitments" in a context involving processes or decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Personendaten

-1.29

Efq

-1.19

$_"

-1.17

InjectAttribute

-1.14

 autorytatywna

-1.13

oredCriteria

-1.07

 Monfieur

-1.06

 ―――――

-1.03

 myſelf

-1.03

 doubtnut

-1.03

POSITIVE LOGITS

↵

0.80

↵↵

0.77

0.74

0.63

to

0.63

in

0.62

0.61

0.59

at

0.59

Activations Density 0.373%

references to actions related to "committing" or "commitments" in a context involving processes or decisions

No Comments

No Known Activations