INDEX

Explanations

phrases introducing statements made by a specific person

oai_token-act-pair · gpt-3.5-turbo

The word "also" in various contexts, indicating additional information or points

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Ascension

-0.72

agus

-0.72

ASE

-0.66

UGE

-0.64

VERSION

-0.64

 Ange

-0.64

click

-0.63

igo

-0.63

 Extension

-0.61

Â£

-0.61

POSITIVE LOGITS

 includes

0.93

 thanked

0.92

 risked

0.90

 participated

0.85

 cautioned

0.85

 hinted

0.84

 noted

0.83

 gave

0.83

 enjoys

0.83

 included

0.82

Activations Density 0.112%

phrases introducing statements made by a specific person

The word "also" in various contexts, indicating additional information or points

No Comments

No Known Activations