INDEX

Explanations

words related to eligibility and capability in various contexts

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

jsonwebtoken

-0.69

UIApplication

-0.60

 apasion

-0.60

 vulgaires

-0.57

INTENANCE

-0.57

SerializedSize

-0.57

titleMargin

-0.57

lichung

-0.55

InSection

-0.55

RegressionTest

-0.55

POSITIVE LOGITS

able

2.50

ABLE

2.04

ability

1.89

pable

1.75

Able

1.73

vable

1.72

eable

1.72

isable

1.71

 able

1.69

izable

1.69

Activations Density 2.654%

words related to eligibility and capability in various contexts

No Comments

No Known Activations