INDEX

Explanations

technical terms or acronyms

oai_token-act-pair · gpt-3.5-turbo

references to specific treatments or substances in a medical or scientific context

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

 Mandela

-0.71

ggies

-0.65

Soy

-0.63

 Sachs

-0.61

visor

-0.58

vised

-0.58

ANC

-0.58

 hars

-0.58

hattan

-0.57

 equity

-0.57

POSITIVE LOGITS

ools

1.05

acular

0.97

inct

0.94

ypes

0.93

rees

0.91

rue

0.90

ral

0.90

rine

0.88

ype

0.88

reme

0.87

Activations Density 0.020%

technical terms or acronyms

references to specific treatments or substances in a medical or scientific context

No Comments

No Known Activations