INDEX

Explanations

phrases or terms that include the word "titled"

oai_token-act-pair · gpt-3.5-turbo

words related to titles or naming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ometers

-0.82

abet

-0.68

othe

-0.66

 Colo

-0.64

orem

-0.64

 Clicker

-0.64

 Schwarz

-0.63

ometer

-0.63

ores

-0.62

į

-0.61

POSITIVE LOGITS

itled

1.00

untled

0.86

named

0.84

ness

0.84

ividual

0.79

selves

0.76

nesses

0.76

terday

0.72

nesday

0.72

ebted

0.71

Activations Density 0.039%

phrases or terms that include the word "titled"

words related to titles or naming

No Comments

No Known Activations