INDEX

Explanations

references to specific names or entities related to a topic

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

sizeCache

-0.71

nements

-0.52

sillon

-0.48

 Reverso

-0.47

 clear

-0.46

Rad

-0.46

 indisponible

-0.46

clear

-0.45

pst

-0.45

WAVE

-0.45

POSITIVE LOGITS

VIAF

0.70

NamedQueries

0.59

 bedo

0.58

 mergeFrom

0.55

MLLoader

0.53

 MainAxisSize

0.52

 ArrayAdapter

0.52

 acidosis

0.52

 createState

0.51

 uLocal

0.51

Activations Density 0.249%

references to specific names or entities related to a topic

No Comments

No Known Activations