INDEX

Explanations

references to prior statements or mentions in the text

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

preceding "previously", "earlier", "above"

np_acts-logits-general · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

UnsafeEnabled

-0.48

localctx

-0.43

 TextAppearance

-0.41

RUnlock

-0.39

guenos

-0.39

現在の

-0.39

mergeFrom

-0.37

expandindo

-0.37

ísticas

-0.36

 modernen

-0.36

POSITIVE LOGITS

 previously

3.02

 previous

2.97

 earlier

2.95

 sebelumnya

2.72

 Previously

2.66

previously

2.64

Previously

2.61

previous

2.58

earlier

2.56

 PREVIOUS

2.48

Activations Density 1.790%

references to prior statements or mentions in the text

preceding "previously", "earlier", "above"

No Comments

No Known Activations