INDEX

Explanations

descriptions of events unfolding or being explained

oai_token-act-pair · gpt-3.5-turbo

questions that seek to understand origins or explanations of events

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

illation

-0.69

arer

-0.68

 fixme

-0.66

rored

-0.66

arers

-0.64

ga

-0.62

cour

-0.61

mented

-0.61

gae

-0.60

auer

-0.60

POSITIVE LOGITS

oslov

0.76

 existence

0.74

 genesis

0.73

 fateful

0.67

 fixation

0.67

agascar

0.62

 conception

0.62

 inception

0.62

olas

0.61

 fascination

0.59

Activations Density 0.329%

descriptions of events unfolding or being explained

questions that seek to understand origins or explanations of events

No Comments

No Known Activations