INDEX

Explanations

terms related to negative experiences or perceptions

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

Negative sentiment or failure

np_acts-logits-general · gemini-2.0-flash

negative outcomes

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

atown

-0.53

 uninterrupted

-0.50

сшта

-0.48

]='\

-0.48

ESTON

-0.47

 undamaged

-0.46

 estekak

-0.45

 undisturbed

-0.45

smooth

-0.45

<>(

-0.45

POSITIVE LOGITS

 worse

0.77

 poor

0.72

 incapable

0.72

 Worse

0.70

 ineffective

0.68

ácara

0.67

 unworthy

0.66

Worse

0.65

 unable

0.65

 incapa

0.64

Activations Density 0.997%

terms related to negative experiences or perceptions

Negative sentiment or failure

negative outcomes

No Comments

No Known Activations