INDEX

Explanations

specific indicators of issues, particularly related to quality or undesirability in various contexts

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

렴

-0.57

 undamaged

-0.57

ález

-0.54

 föruts

-0.53

gonic

-0.52

 καλ

-0.52

NonNull

-0.51

agus

-0.51

spora

-0.50

ziplin

-0.50

POSITIVE LOGITS

StructEnd

0.75

 worse

0.68

 mauvaise

0.67

 mauvais

0.66

 Worse

0.63

😖

0.60

JSONException

0.60

👎

0.60

 improper

0.58

버

0.58

Activations Density 1.134%

specific indicators of issues, particularly related to quality or undesirability in various contexts

No Comments

No Known Activations