INDEX

Explanations

the mention of significant 'firsts' or milestones achieved by individuals or entities

oai_token-act-pair · gpt-3.5-turbo

references to significant first occurrences or notable distinctions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

utics

-0.80

utils

-0.73

terness

-0.72

 abound

-0.70

,,,,,,,,

-0.70

nit

-0.68

ĺħ

-0.68

asty

-0.68

 Diseases

-0.67

prone

-0.66

POSITIVE LOGITS

 foray

1.07

 hurdle

0.93

 outing

0.93

 ever

0.87

 casualty

0.87

 attempt

0.86

 sighting

0.86

 manifestation

0.86

 ascent

0.84

 introdu

0.84

Activations Density 0.177%

the mention of significant 'firsts' or milestones achieved by individuals or entities

references to significant first occurrences or notable distinctions

No Comments

No Known Activations