INDEX

Explanations

phrases related to launching or introducing new products or services

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the release or deployment of products or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

cious

-0.89

hai

-0.63

ippi

-0.63

antry

-0.63

shaw

-0.61

 Arche

-0.60

Ë

-0.60

Mub

-0.59

pert

-0.59

efe

-0.59

POSITIVE LOGITS

casts

0.85

wards

0.85

 Archdemon

0.85

 invitations

0.73

pad

0.66

 notifications

0.65

 schedule

0.65

sheets

0.65

fitted

0.64

 fireworks

0.63

Activations Density 0.028%

phrases related to launching or introducing new products or services

phrases indicating the release or deployment of products or services

No Comments

No Known Activations