INDEX

Explanations

phrases centered around taking action or making decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 care

-0.44

故

-0.44

findpost

-0.43

 soldati

-0.43

cabul

-0.43

[]):

-0.42

пита

-0.42

Capture

-0.41

__:

-0.41

歴

-0.41

POSITIVE LOGITS

 leap

1.00

MemoryWarning

0.82

Autoritní

0.76

 Leap

0.75

 step

0.75

 stance

0.74

leap

0.73

MigrationBuilder

0.72

 plunge

0.72

 stab

0.71

Activations Density 0.123%

phrases centered around taking action or making decisions

No Comments

No Known Activations