INDEX

Explanations

statements related to actions or events happening to certain entities

oai_token-act-pair · gpt-3.5-turbo

various forms of the verb "to be."

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

 IMAGES

-0.68

 Yourself

-0.67

 violates

-0.66

 Prepar

-0.64

 Unless

-0.64

ãĢı

-0.63

 Acquisition

-0.62

 Ends

-0.59

 Defeat

-0.59

Â®

-0.59

POSITIVE LOGITS

 likewise

1.16

 meanwhile

1.09

 similarly

0.99

 also

0.84

onite

0.80

 notably

0.75

 attest

0.73

 reportedly

0.72

 doubtless

0.70

ŃĶ

0.70

Activations Density 0.736%

statements related to actions or events happening to certain entities

various forms of the verb "to be."

No Comments

No Known Activations