INDEX

Explanations

numbers at the end of sentences

oai_token-act-pair · gpt-3.5-turbo

numerical identifiers or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

undai

-0.95

entry

-0.76

raltar

-0.75

perm

-0.74

efficients

-0.72

otaur

-0.67

 neighb

-0.66

oppy

-0.66

 millenn

-0.66

kered

-0.65

POSITIVE LOGITS

1.02

0.86

APH

0.82

Â¢

0.78

oran

0.78

0.76

%-

0.74

0.73

Activations Density 0.031%

numbers at the end of sentences

numerical identifiers or statistics

No Comments

No Known Activations