INDEX

Explanations

references to individuals and their interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

chequer

-0.63

rhein

-0.58

 Seti

-0.55

ImageField

-0.55

Sev

-0.55

đu

-0.53

Rhein

-0.53

nodoc

-0.52

PRIMARY

-0.52

databind

-0.51

POSITIVE LOGITS

addCriterion

0.84

 knows

0.75

 anything

0.70

Rhestr

0.69

 formules

0.69

MessageTagHelper

0.68

Havolalar

0.68

 understands

0.67

EndProject

0.67



0.66

Activations Density 0.080%

references to individuals and their interactions

No Comments

No Known Activations