INDEX

Explanations

mentions of the word "octopus"

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "opus"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 counseling

-0.70

 homes

-0.68

 warning

-0.66

 safety

-0.66

 Cert

-0.65

 distance

-0.65

 residences

-0.65

 reminding

-0.64

 remed

-0.62

 areas

-0.62

POSITIVE LOGITS

opus

4.75

opter

1.14

ebra

1.14

asus

1.11

ĸļ

1.09

ulhu

1.09

aurus

1.06

 squid

1.04

iatus

1.02

opy

1.00

Activations Density 0.021%

mentions of the word "octopus"

mentions of the term "opus"

No Comments

No Known Activations