INDEX

Explanations

mentions of or references to visual content such as photos

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Photos."

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

ministic

-0.75

oshenko

-0.74

stood

-0.65

merce

-0.64

 speech

-0.64

phas

-0.63

rance

-0.63

pled

-0.62

lag

-0.62

 Hutchinson

-0.62

POSITIVE LOGITS

ynthesis

0.92

Gallery

0.84

 Photos

0.82

Photos

0.76

 Caption

0.75

Ø³

0.75

iew

0.72

ynt

0.71

OTOS

0.68

uties

0.66

Activations Density 0.013%

mentions of or references to visual content such as photos

occurrences of the word "Photos."

No Comments

No Known Activations