INDEX

Explanations

research-related phrases, particularly focusing on analyzing data and studying effects

oai_token-act-pair · gpt-3.5-turbo

references to research studies and their findings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

scribe

-0.82

yg

-0.73

shall

-0.73

usercontent

-0.70

still

-0.70

argon

-0.69

 guiName

-0.68

estate

-0.67

walker

-0.66

youtu

-0.64

POSITIVE LOGITS

 hypotheses

0.84

 hypothesis

0.80

RNA

0.80

 genomic

0.80

avorite

0.78

 simulations

0.75

 mice

0.75

 statistical

0.74

ĵĺ

0.73

 correlations

0.73

Activations Density 0.262%

research-related phrases, particularly focusing on analyzing data and studying effects

references to research studies and their findings

No Comments

No Known Activations