INDEX

Explanations

actions or interactions between individuals or groups

oai_token-act-pair · gpt-3.5-turbo

instances of direct speech or quotations

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

cair

-0.74

aters

-0.68

amental

-0.66

haven

-0.64

atic

-0.63

agate

-0.59

estine

-0.59

abiding

-0.58

atin

-0.57

yy

-0.57

POSITIVE LOGITS

 paraph

0.75

 rhet

0.74

 chuck

0.73

 laughter

0.69

 interviewer

0.68

 introductory

0.68

 quoted

0.67

 pione

0.67

 lect

0.63

 sarcast

0.63

Activations Density 0.179%

actions or interactions between individuals or groups

instances of direct speech or quotations

No Comments

No Known Activations