INDEX

Explanations

instances of the word "pattern" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

sizeCache

-0.87

!("{

-0.74

UnusedPrivate

-0.65

RemoteException

-0.62

 CURLOPT

-0.60

 bezig

-0.59

SwingConstants

-0.58

 cáp

-0.58

blå

-0.57

CURLOPT

-0.56

POSITIVE LOGITS

 patterns

1.17

 Patterns

1.08

Patterns

1.04

patterns

0.96

 PATTERN

0.92

 pattern

0.91

 Pattern

0.85

TERNS

0.77

pattern

0.77

Pattern

0.70

Activations Density 0.092%

instances of the word "pattern" and its variations

No Comments

No Known Activations