INDEX

Explanations

the word "screen" with different variations in the text

oai_token-act-pair · gpt-3.5-turbo

mentions of "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 @ 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

doms

-0.77

ortium

-0.71

aternal

-0.71

ghan

-0.65

 caution

-0.64

IGH

-0.62

ipop

-0.62

onomic

-0.61

 antid

-0.61

 Harriet

-0.60

POSITIVE LOGITS

plays

1.35

printed

1.04

tops

1.02

writers

1.00

writer

0.99

grab

0.96

caps

0.96

TVs

0.94

 screens

0.92

writing

0.91

Activations Density 0.030%

the word "screen" with different variations in the text

mentions of "screen" in various contexts

No Comments

No Known Activations