INDEX

Explanations

terms related to "occupation" and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

شهاد

-0.83

 Vish

-0.80

 Chet

-0.80

Vish

-0.77

 AssemblyCulture

-0.76

ddha

-0.72

ibatis

-0.71

mtable

-0.71

 humeur

-0.70

Portail

-0.70

POSITIVE LOGITS

VAC

0.91

 Fiction

0.84

 fiction

0.84

 occupa

0.83

VAC

0.82

Occupation

0.79

ITION

0.79

 fractions

0.78

vac

0.78

fiction

0.78

Activations Density 0.317%

terms related to "occupation" and its variations in different contexts

No Comments

No Known Activations