INDEX

Explanations

terms associated with evaluation and criticism

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 الحره

-0.82

TypedDataSet

-0.66

niająca

-0.65

bootstrapcdn

-0.64

 transfieras

-0.63

RenderAtEndOf

-0.62

SequentialGroup

-0.59

PerformLayout

-0.58

intero

-0.56

__;

-0.56

POSITIVE LOGITS

 constitution

0.62

ingly

0.61

dly

0.60

 shrew

0.59

 constitutions

0.58

abyrinth

0.57

 chao

0.56

őd

0.56

 parades

0.56

liness

0.55

Activations Density 0.396%

terms associated with evaluation and criticism

No Comments

No Known Activations