INDEX

Explanations

time durations expressed in minutes

oai_token-act-pair · gpt-3.5-turbo

time-related measurements and durations

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

ĸļ

-0.85

Äĩ

-0.72

 Intent

-0.66

kok

-0.65

ãĥ£

-0.63

 Charter

-0.63

 PROG

-0.62

ettings

-0.61

gha

-0.59

etsk

-0.59

POSITIVE LOGITS

ruary

0.89

0.71

STE

0.69

ish

0.68

owship

0.68

 Spartans

0.66

cia

0.66

ancers

0.65

annabin

0.64

oppers

0.63

Activations Density 0.228%

time durations expressed in minutes

time-related measurements and durations

No Comments

No Known Activations