INDEX

Explanations

terms related to "subject" or "topic" within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 craw

-0.78

✨:

-0.76

 flocc

-0.75

 dandy

-0.75

 Athenians

-0.73

раздо

-0.73

ForRow

-0.73

 himſelf

-0.68

SPS

-0.66

 greased

-0.66

POSITIVE LOGITS

 subject

1.83

 Subject

1.72

 subjects

1.70

subject

1.70

 SUBJECT

1.64

Subject

1.62

 Subjects

1.61

SUBJECT

1.58

Subjects

1.53

setSubject

1.49

Activations Density 0.054%

terms related to "subject" or "topic" within the text

No Comments

No Known Activations