INDEX

Explanations

positive emotions or expressions of gratitude

oai_token-act-pair · gpt-3.5-turbo

expressions of gratitude and appreciation

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

enges

-0.74

eworthy

-0.69

ELD

-0.65

ftime

-0.64

 Russo

-0.62

uner

-0.62

amental

-0.61

velength

-0.61

arching

-0.60

 Glob

-0.60

POSITIVE LOGITS

'll

0.93

 didnt

0.90

 hadn

0.88

 didn

0.88

'd

0.86

're

0.84

've

0.82

 could

0.81

 forgot

0.80

 wouldn

0.80

Activations Density 0.229%

positive emotions or expressions of gratitude

expressions of gratitude and appreciation

No Comments

No Known Activations