INDEX

Explanations

phrases related to geographical locations

oai_token-act-pair · gpt-3.5-turbo

punctuation marks, specifically commas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

olves

-0.66

ror

-0.66

itiveness

-0.65

ivable

-0.64

 direction

-0.63

attribute

-0.63

units

-0.63

overs

-0.62

isitions

-0.62

urrection

-0.61

POSITIVE LOGITS

 Duchess

1.00

LLP

0.97

 Calif

0.91

 Colo

0.91

NJ

0.85

 supra

0.85

TX

0.84

Md

0.81

nee

0.80

Ont

0.79

Activations Density 0.129%

phrases related to geographical locations

punctuation marks, specifically commas

No Comments

No Known Activations