INDEX

Explanations

references to items or activities that are extra or additional

oai_token-act-pair · gpt-3.5-turbo

instances and discussions of the term "spare" 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

anwhile

-0.83

sein

-0.74

 appropri

-0.72

stasy

-0.69

inatory

-0.68

essee

-0.68

ablishment

-0.67

SOURCE

-0.67

uador

-0.66

iggurat

-0.65

POSITIVE LOGITS

liest

0.90

ware

0.80

 tire

0.77

 spare

0.75

plane

0.72

pering

0.69

bon

0.69

 tyre

0.68

ricular

0.67

 Bees

0.66

Activations Density 0.026%

references to items or activities that are extra or additional

instances and discussions of the term "spare" in various contexts

No Comments

No Known Activations