INDEX

Explanations

instances of the word "cut" and its variations, indicating a focus on actions involving cutting or reductions

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

"cut"

np_acts-logits-general · gemini-2.0-flash

cut, cuts, cutting, carved

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

 doInBackground

-0.86

principalTable

-0.85

DockStyle

-0.80

"}")

-0.80

WebElementEntity

-0.77

таратура

-0.73

AndEndTag

-0.70

abestanden

-0.70

complexContent

-0.68

 AssemblyVersion

-0.65

POSITIVE LOGITS

cut

1.70

Cut

1.66

CUT

1.64

 cuts

1.60

cut

1.57

 cutting

1.56

cuts

1.56

Cut

1.52

CUT

1.48

 Cutting

1.46

Activations Density 0.120%

instances of the word "cut" and its variations, indicating a focus on actions involving cutting or reductions

"cut"

cut, cuts, cutting, carved

No Comments

No Known Activations