INDEX

Explanations

mentions of camping-related activities or locations

oai_token-act-pair · gpt-3.5-turbo

references to camps and camping activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

lihood

-0.75

 latent

-0.61

 quot

-0.61

 antioxid

-0.61

 resurg

-0.60

 streng

-0.60

piring

-0.59

 Fiction

-0.58

 magnification

-0.57

 republic

-0.57

POSITIVE LOGITS

fires

1.51

grounds

1.48

ground

1.45

fire

1.32

camp

1.11

agna

1.04

agne

1.04

ites

1.04

bell

1.01

anas

0.97

Activations Density 0.032%

mentions of camping-related activities or locations

references to camps and camping activities

No Comments

No Known Activations