INDEX

Explanations

terms and phrases related to natural habitats and conservation efforts

oai_token-act-pair · gpt-3.5-turbo

references to habitats and their conservation

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ivan

-0.75

ining

-0.72

inness

-0.69

otten

-0.68

agher

-0.67

ahon

-0.66

ochet

-0.65

racted

-0.65

ripp

-0.64

 satirical

-0.64

POSITIVE LOGITS

 habitat

1.19

 habitats

1.04

conservancy

0.84

 ecosystems

0.78

 dwell

0.78

 vegetation

0.77

 ecology

0.76

 dwelling

0.71

 Environment

0.71

 flora

0.71

Activations Density 0.013%

terms and phrases related to natural habitats and conservation efforts

references to habitats and their conservation

No Comments

No Known Activations