INDEX

Explanations

terms related to categories or groups

oai_token-act-pair · gpt-3.5-turbo

references to brackets and related symbols

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

natureconservancy

-0.85

cart

-0.69

mington

-0.68

 Antar

-0.64

 Nare

-0.63

mit

-0.63

Ay

-0.63

 Gaul

-0.60

Soy

-0.60

 VIDEOS

-0.59

POSITIVE LOGITS

ackets

1.05

 bracket

1.02

 brackets

1.02

acket

0.96

uled

0.78

sheets

0.74

icter

0.69

 stuffing

0.69

ItemTracker

0.68

umbered

0.68

Activations Density 0.026%

terms related to categories or groups

references to brackets and related symbols

No Comments

No Known Activations