INDEX

Explanations

numerical measurements expressed using the number "180"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the number 180, likely in the context of measurements or temperatures

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

ensional

-0.82

oru

-0.77

icism

-0.75

scape

-0.75

hower

-0.74

iche

-0.74

orc

-0.72

book

-0.72

achable

-0.72

zig

-0.72

POSITIVE LOGITS

 ILCS

0.90

Âº

0.77

 degrees

0.74

Â°

0.72

 burner

0.71

lbs

0.70

 SHARES

0.70

mph

0.69

 pounds

0.68

NAT

0.68

Activations Density 0.023%

numerical measurements expressed using the number "180"

occurrences of the number 180, likely in the context of measurements or temperatures

No Comments

No Known Activations