INDEX

Explanations

phrases related to evaluation or comparison

oai_token-act-pair · gpt-3.5-turbo

clauses that use the word "which"

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

Bed

-0.79

politics

-0.70

let

-0.69

 VIDEOS

-0.63

 Baker

-0.63

Ott

-0.62

 Vent

-0.61

mob

-0.60

 Bucc

-0.60

STE

-0.59

POSITIVE LOGITS

soever

1.06

 resulted

0.84

 exposes

0.82

 comprises

0.81

 brings

0.78

 attracts

0.75

 contains

0.75

 enables

0.75

xual

0.74

assic

0.74

Activations Density 0.083%

phrases related to evaluation or comparison

clauses that use the word "which"

No Comments

No Known Activations