INDEX

Explanations

terms related to eligibility and criteria 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 @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 makeStyles

-0.74

<tfoot>

-0.72

/]

-0.66

 Koll

-0.65

"][

-0.65

?”,

-0.64

']?>

-0.64

 Scand

-0.62

therly

-0.62

]--;

-0.61

POSITIVE LOGITS

 criteria

1.05

 criterion

0.93

criteria

0.85

 eligible

0.81

 ineligible

0.79

 eligibility

0.79

 Criteria

0.71

Eligibility

0.70

 Eligibility

0.69

 Eligible

0.68

Activations Density 0.078%

terms related to eligibility and criteria in various contexts

No Comments

No Known Activations