INDEX

Explanations

words related to awards, recognition, and praise

oai_token-act-pair · gpt-3.5-turbo

words related to awards and recognition

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

£ı

-0.69

oppy

-0.69

ascus

-0.66

 Sunny

-0.65

eland

-0.64

 Trout

-0.63

 Wolfe

-0.63

 Cree

-0.62

fo

-0.61

 Stur

-0.61

POSITIVE LOGITS

giving

0.84

 recipients

0.82

abilia

0.80

edly

0.80

 forgiveness

0.77

 recipient

0.76

onement

0.74

payers

0.74

 holders

0.73

itism

0.73

Activations Density 0.212%

words related to awards, recognition, and praise

words related to awards and recognition

No Comments

No Known Activations