INDEX

Explanations

mentions of words related to screens or scripts

oai_token-act-pair · gpt-3.5-turbo

references to "screen" or "screenwriters."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ipop

-0.74

ortium

-0.72

doms

-0.71

ghan

-0.71

 Harriet

-0.69

 deleg

-0.68

IGH

-0.67

ciating

-0.66

thens

-0.64

 hypoc

-0.63

POSITIVE LOGITS

plays

1.28

 screens

1.05

screen

1.04

 screen

1.00

writers

0.97

writer

0.95

TVs

0.95

room

0.87

 Screen

0.85

reens

0.83

Activations Density 0.012%

mentions of words related to screens or scripts

references to "screen" or "screenwriters."

No Comments

No Known Activations