INDEX

Explanations

individual items or entities being excluded, made, or not included in a certain context or list

oai_token-act-pair · gpt-3.5-turbo

content related to exclusion from studies or assessments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

him

-0.68

 ILCS

-0.68

mercial

-0.65

 spir

-0.62

 increasingly

-0.62

ilitating

-0.61

ãĤ¶

-0.60

ãĥĸ

-0.58

rowth

-0.58

 beginnings

-0.58

POSITIVE LOGITS

 finalists

0.98

 panel

0.88

 surveyed

0.88

 semif

0.87

 participant

0.85

 omitted

0.84

 selections

0.83

 delegation

0.83

 participants

0.81

 turnout

0.79

Activations Density 0.648%

individual items or entities being excluded, made, or not included in a certain context or list

content related to exclusion from studies or assessments

No Comments

No Known Activations