INDEX

Explanations

specific numerical codes or indicators

oai_token-act-pair · gpt-3.5-turbo

the repetition of the letter "K" 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 @ 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

 expires

-0.69

terday

-0.68

 diapers

-0.65

ãĥ¼ãĥĨãĤ£

-0.63

 bottleneck

-0.62

 decay

-0.61

acebook

-0.61

 medieval

-0.61

ÙĴ

-0.59

cipl

-0.58

POSITIVE LOGITS

laus

1.06

irk

1.06

EEP

1.04

rieg

1.04

won

1.03

orea

1.01

essel

1.00

ernel

0.98

eeper

0.97

idding

0.97

Activations Density 0.033%

specific numerical codes or indicators

the repetition of the letter "K" in various contexts

No Comments

No Known Activations