INDEX

Explanations

numerical quantities presented as percentages or counts

oai_token-act-pair · gpt-3.5-turbo

phrases or references to the number one hundred

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ngth

-0.80

oles

-0.78

rift

-0.77

olas

-0.77

rang

-0.73

letal

-0.73

achi

-0.72

attled

-0.70

colm

-0.70

isen

-0.70

POSITIVE LOGITS

1.15

%"

0.95

%]

0.93

0.91

 milliseconds

0.89

0.88

%);

0.86

=#

0.86

 watts

0.82

Activations Density 0.019%

numerical quantities presented as percentages or counts

phrases or references to the number one hundred

No Comments

No Known Activations