INDEX

Explanations

mentions of screens or screen-related activities

oai_token-act-pair · gpt-3.5-turbo

instances of the word "screen" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ghan

-0.72

doms

-0.70

 Carnegie

-0.67

 caution

-0.65

ortium

-0.65

IGH

-0.63

 plur

-0.62

lesh

-0.61

 Harriet

-0.60

aternal

-0.59

POSITIVE LOGITS

plays

1.34

printed

1.06

writers

1.03

tops

1.00

caps

0.96

writer

0.96

TVs

0.96

writing

0.91

 screens

0.90

reens

0.89

Activations Density 0.019%

mentions of screens or screen-related activities

instances of the word "screen" in various contexts

No Comments

No Known Activations