INDEX

Explanations

quantitative comparisons and numerical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

LayoutConstraint

-0.59

RegressionTest

-0.53

writeFieldEnd

-0.53

 Smol

-0.52

InputChange

-0.52

placer

-0.51

StrictMode

-0.51

ActionMode

-0.50

Tag

-0.50

 متعلقه

-0.49

POSITIVE LOGITS

 للاسماء

0.70

 fewer

0.66

WithMany

0.61

 }}"></

0.60

OGND

0.59

Rptr

0.59

 nemá

0.59

 genügend

0.58

więcej

0.57

 Rptr

0.56

Activations Density 0.305%

quantitative comparisons and numerical data

No Comments

No Known Activations