INDEX

Explanations

references to "head" in various contexts related to injuries or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

makeConstraints

-0.91

Eloquent

-0.87

matchCondition

-0.77

 vPvB

-0.76

 Roskov

-0.73

 MotionEvent

-0.72

 CURLOPT

-0.71

 resourceCulture

-0.70

География

-0.70

')";

-0.70

POSITIVE LOGITS

 head

1.20

 Head

1.05

head

1.04

Head

1.00

 голову

0.84

 heads

0.82

HEAD

0.81

 HEAD

0.79

头

0.78

 cabeza

0.76

Activations Density 0.224%

references to "head" in various contexts related to injuries or conditions

No Comments

No Known Activations