INDEX

Explanations

quantitative terms and measurements

oai_token-act-pair · gpt-3.5-turbo

terms related to quantification and measurement 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

HOME

-0.84

lihood

-0.77

 Archdemon

-0.69

 blades

-0.68

 spare

-0.65

 Mansion

-0.62

aples

-0.60

nen

-0.60

 Odin

-0.60

Fav

-0.59

POSITIVE LOGITS

itatively

1.43

 quant

1.08

imet

1.05

ifiable

1.01

itative

0.92

idian

0.91

ified

0.88

eros

0.86

ifies

0.85

rill

0.82

Activations Density 0.015%

quantitative terms and measurements

terms related to quantification and measurement in various contexts

No Comments

No Known Activations