INDEX

Explanations

words ending in 'll featuring varying activation values from 8 to 10

oai_token-act-pair · gpt-3.5-turbo

words or phrases that contain the substring "ll"

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

EStream

-0.77

lished

-0.73

 guiActiveUn

-0.73

¥µ

-0.70

cknow

-0.70

hered

-0.67

ItemTracker

-0.66

ciating

-0.66

¥ŀ

-0.66

quo

-0.65

POSITIVE LOGITS

uminati

1.19

ounge

1.15

oyd

1.15

owship

1.03

iard

1.01

sburgh

0.98

ateral

0.98

ibrary

0.96

ows

0.96

inois

0.94

Activations Density 0.027%

words ending in 'll featuring varying activation values from 8 to 10

words or phrases that contain the substring "ll"

No Comments

No Known Activations