INDEX

Explanations

variations of the word "to"

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

Concluding Remarks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

нгред

-0.91

jspb

-0.90

يكب

-0.87

 propOrder

-0.86

iſen

-0.86

 FetchType

-0.85

StoryboardSegue

-0.85

featureID

-0.85

OGND

-0.85

 يتيمه

-0.85

POSITIVE LOGITS

0.39

0.38

br

0.37

ys

0.36

↵

0.35

“

0.35

Activations Density 0.000%

variations of the word "to"

Concluding Remarks

No Comments

No Known Activations

variations of the word "to"

Concluding Remarks

No Comments

No Known Activations