INDEX

Explanations

positive evaluations of experiences or outcomes

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

Follows "Q:" or "Section" or contains non-English words

np_acts-logits-general · gemini-2.0-flash

conditions

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

dafx

-0.60

Externé

-0.54

thousands

-0.51

unless

-0.51

hundreds

-0.48

 hundreds

-0.48

 thousands

-0.47

ugly

-0.46

Izvori

-0.46

 Blame

-0.46

POSITIVE LOGITS

 estimés

0.70

 benefitted

0.67

 benefited

0.64

 aprend

0.62

 mentors

0.62

 Aprend

0.62

 enriquec

0.61

 enri

0.60

󠁴

0.60

 enriching

0.60

Activations Density 0.170%

positive evaluations of experiences or outcomes

Follows "Q:" or "Section" or contains non-English words

conditions

No Comments

No Known Activations