INDEX

Explanations

praise or positive feedback about different subjects

oai_token-act-pair · gpt-3.5-turbo

statements that express the positive attributes or essence of various subjects

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

Beg

-0.66

ansen

-0.63

 awaits

-0.61

ut

-0.60

addons

-0.60

en

-0.60

iates

-0.60

eor

-0.59

 shops

-0.58

atche

-0.58

POSITIVE LOGITS

 undoubtedly

0.85

\\\\\\\\

0.78

 indeed

0.76

 actually

0.75

Magikarp

0.72

 definitely

0.72

 probably

0.70

KER

0.68

itchie

0.67

 still

0.66

Activations Density 0.159%

praise or positive feedback about different subjects

statements that express the positive attributes or essence of various subjects

No Comments

No Known Activations