INDEX

Explanations

terms related to scientific measurements and concepts

oai_token-act-pair · gpt-3.5-turbo

the conjunction "and" in various contexts

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

anza

-0.53

 Voters

-0.53

je

-0.53

Doug

-0.53

leg

-0.53

 Belfast

-0.53

gem

-0.52

irt

-0.51

nt

-0.51

POSITIVE LOGITS

 consequently

0.79

 therefore

0.73

its

0.72

 hence

0.69

APD

0.68

 other

0.68

 adjoining

0.68

 thus

0.67

 indeed

0.66

 related

0.63

Activations Density 0.381%

terms related to scientific measurements and concepts

the conjunction "and" in various contexts

No Comments

No Known Activations