INDEX

Explanations

dates expressed in simple forms

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "greens" and related variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 sarc

-0.72

 belt

-0.69

 accident

-0.65

 bust

-0.64

 Sherlock

-0.64

 Anat

-0.63

 class

-0.62

act

-0.59

 historical

-0.59

Dom

-0.59

POSITIVE LOGITS

reens

4.65

reen

1.69

 Greens

1.42

reenshots

1.21

 greens

1.19

owers

1.06

ttes

1.06

roups

1.03

rists

1.02

anners

1.01

Activations Density 0.012%

dates expressed in simple forms

occurrences of the term "greens" and related variations

No Comments

No Known Activations