INDEX

Explanations

words that are interspersed or interleaved within a sequence

oai_token-act-pair · gpt-3.5-turbo

instances of the substring "sp" within words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ãĥĥãĥĪ

-0.79

ĪĴ

-0.78

âĸ¬âĸ¬

-0.73

 behold

-0.71

sbm

-0.71

WAYS

-0.67

vironment

-0.66

hof

-0.65

 Brotherhood

-0.64

naissance

-0.64

POSITIVE LOGITS

atial

1.13

iral

1.09

iegel

1.05

aghetti

1.04

acious

1.04

encer

1.02

acer

1.00

onge

0.99

ending

0.97

ooky

0.95

Activations Density 0.020%

words that are interspersed or interleaved within a sequence

instances of the substring "sp" within words

No Comments

No Known Activations