INDEX

Explanations

expressions of gratitude and thanks

oai_token-act-pair · gpt-3.5-turbo

expressions of gratitude or thanks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

place

-0.80

Ranked

-0.77

ember

-0.77

conserv

-0.76

opers

-0.71

dq

-0.69

objects

-0.67

ther

-0.66

wide

-0.65

hazard

-0.64

POSITIVE LOGITS

giving

0.97

fulness

0.87

God

0.82

 donors

0.81

ESCO

0.80

 contributors

0.80

 colleagues

0.77

 constituents

0.76

 thank

0.73

FUL

0.73

Activations Density 0.022%

expressions of gratitude and thanks

expressions of gratitude or thanks

No Comments

No Known Activations