INDEX

Explanations

references to possible issues or obstacles

oai_token-act-pair · gpt-3.5-turbo

indications of reluctance or resistance in decision-making contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

-0.74

ogie

-0.58

ãĤ«

-0.53

displayText

-0.52

verend

-0.50

igi

-0.49

ãĤ©

-0.49

ãģ®éŃĶ

-0.49

EH

-0.48

UFF

-0.48

POSITIVE LOGITS

 someday

1.21

 sooner

0.81

 tomorrow

0.76

 anytime

0.73

 depending

0.65

 rethink

0.65

 sometime

0.64

ivably

0.63

 somew

0.62

if

0.62

Activations Density 1.691%

references to possible issues or obstacles

indications of reluctance or resistance in decision-making contexts

No Comments

No Known Activations