INDEX

Explanations

specific terms related to organizations and programs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

featureID

-0.75

TypedDataSet

-0.74

 CreateTagHelper

-0.74

fromnode

-0.72

IsContent

-0.69

GraphicsUnit

-0.69

rungsseite

-0.68

ReusableCell

-0.66

awtextra

-0.65

setVerticalGroup

-0.64

POSITIVE LOGITS

ra

0.52

ba

0.50

ral

0.49

ban

0.48

ait

0.47

ila

0.47

ról

0.45

ot

0.45

ból

0.43

 Eind

0.43

Activations Density 0.058%

specific terms related to organizations and programs

No Comments

No Known Activations