INDEX

Explanations

reflexive pronouns related to self-identity and self-perception

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

تیب

-0.63

ectady

-0.63

 themselves

-0.63

 quæ

-0.60

 MessageBoxIcon

-0.60

 kteří

-0.58

SBATCH

-0.58

er

-0.57

StoryboardSegue

-0.56

DockStyle

-0.56

POSITIVE LOGITS

SELF

0.77

skraft

0.64

standig

0.63

selves

0.62

naw

0.61

ändig

0.60

 Paglinawan

0.60

ELF

0.58

Referências

0.57

QMetaType

0.54

Activations Density 0.060%

reflexive pronouns related to self-identity and self-perception

No Comments

No Known Activations