INDEX

Explanations

adjectives describing the intensity or degree of something

oai_token-act-pair · gpt-3.5-turbo

phrases highlighting valuable or notable attributes and characteristics

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

idth

-0.71

ngth

-0.71

berra

-0.69

ysis

-0.66

ength

-0.66

!/

-0.66

PsyNetMessage

-0.65

 Cosponsors

-0.62

ibrary

-0.62

 intervals

-0.61

POSITIVE LOGITS

 worthwhile

0.84

cone

0.73

 centerpiece

0.73

 attractive

0.72

 richer

0.70

 viable

0.67

 honorary

0.67

achable

0.67

 usable

0.67

competitive

0.66

Activations Density 0.177%

adjectives describing the intensity or degree of something

phrases highlighting valuable or notable attributes and characteristics

No Comments

No Known Activations