INDEX

Explanations

dates represented in a specific format

oai_token-act-pair · gpt-3.5-turbo

specific numerical and technical references or identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Reed

-0.69

 doubling

-0.66

thodox

-0.66

ÃĤ

-0.65

 Belt

-0.64

 Crowley

-0.63

 Bowen

-0.62

 compounded

-0.62

 actionGroup

-0.61

 Mayo

-0.60

POSITIVE LOGITS

/)

1.14

/?

1.03

/.

1.01

/#

0.96

ascript

0.95

/,

0.93

/"

0.91

0.87

_(

0.86

_-_

0.79

Activations Density 0.137%

dates represented in a specific format

specific numerical and technical references or identifiers

No Comments

No Known Activations