INDEX

Explanations

phrases related to government actions or decisions

oai_token-act-pair · gpt-3.5-turbo

instances of 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 @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

sburg

-0.74

½

-0.69

ety

-0.69

olves

-0.69

lymp

-0.68

addafi

-0.67

lyn

-0.65

pec

-0.64

usp

-0.63

umen

-0.63

POSITIVE LOGITS

 which

1.70

which

1.35

 dubbed

1.13

 whose

1.07

 whereby

1.06

 wherein

1.04

 Which

0.99

 titled

0.95

 nicknamed

0.92

 albeit

0.91

Activations Density 0.312%

phrases related to government actions or decisions

instances of punctuation marks, specifically commas

No Comments

No Known Activations