INDEX

Explanations

words related to connections or establishing relationships

oai_token-act-pair · gpt-3.5-turbo

words related to connections or links between entities or concepts

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

cheat

-0.69

yy

-0.63

stadt

-0.60

sburg

-0.57

grad

-0.56

,-

-0.56

sv

-0.55

 meantime

-0.54

sburgh

-0.54

_-

-0.53

POSITIVE LOGITS

 dots

0.90

 seamlessly

0.78

uce

0.75

 them

0.70

anooga

0.67

icut

0.66

olate

0.66

 disparate

0.65

links

0.63

 between

0.63

Activations Density 0.087%

words related to connections or establishing relationships

words related to connections or links between entities or concepts

No Comments

No Known Activations