INDEX

Explanations

references to offers or offerings

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "offered" and its variations

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

igue

-0.85

cation

-0.65

isol

-0.64

set

-0.63

bred

-0.61

cling

-0.61

 habit

-0.61

ineries

-0.58

sis

-0.58

CLE

-0.58

POSITIVE LOGITS

 condolences

1.02

 suggestions

0.84

 advice

0.75

jri

0.74

 refunds

0.73

ensical

0.71

 encouragement

0.71

 insight

0.70

 unequiv

0.70

 testim

0.69

Activations Density 0.034%

references to offers or offerings

occurrences of the word "offered" and its variations

No Comments

No Known Activations