INDEX

Explanations

phrases related to physical positions or locations

oai_token-act-pair · gpt-3.5-turbo

references to spatial positioning or metaphorical 'front' and 'back' 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

ritch

-0.74

lectic

-0.71

ortium

-0.67

swick

-0.67

anmar

-0.64

upon

-0.62

CHQ

-0.61

phis

-0.60

byter

-0.60

emort

-0.60

POSITIVE LOGITS

 heels

0.86

 leash

0.83

 basis

0.82

 occasions

0.82

 shelf

0.80

ilts

0.77

 side

0.76

 verge

0.75

 sidelines

0.74

 behalf

0.72

Activations Density 0.130%

phrases related to physical positions or locations

references to spatial positioning or metaphorical 'front' and 'back' concepts

No Comments

No Known Activations