INDEX

Explanations

years or descriptions related to in-depth analysis, reports, or studies

oai_token-act-pair · gpt-3.5-turbo

references to thorough and detailed evaluations or analyses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

artifacts

-0.69

ween

-0.68

birds

-0.66

zees

-0.66

igg

-0.65

hao

-0.64

 cramped

-0.62

 indirectly

-0.62

rooms

-0.62

hops

-0.62

POSITIVE LOGITS

bred

1.21

rehensive

1.09

 overhaul

1.02

 overview

0.97

 examination

0.96

 evaluation

0.89

 analysis

0.87

 comprehensive

0.86

 assessment

0.85

endium

0.83

Activations Density 0.089%

years or descriptions related to in-depth analysis, reports, or studies

references to thorough and detailed evaluations or analyses

No Comments

No Known Activations