INDEX

Explanations

information related to quantities and measurements

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate approximate quantities or measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Peaks

-0.68

Express

-0.67

BT

-0.66

ode

-0.61

glas

-0.59

 Junction

-0.59

hesis

-0.59

NEY

-0.59

ocy

-0.57

chens

-0.56

POSITIVE LOGITS

 halfway

0.93

0.89

 Â½

0.86

 half

0.84

0.83

etheless

0.83

0.82

 eighty

0.82

Activations Density 0.062%

information related to quantities and measurements

phrases that indicate approximate quantities or measurements

No Comments

No Known Activations