INDEX

Explanations

mentions of terms related to environmental cleanliness and regulatory acts

oai_token-act-pair · gpt-3.5-turbo

references to environmental regulations or policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

pton

-0.69

yip

-0.67

Bone

-0.67

ONT

-0.66

otos

-0.65

doms

-0.64

eryl

-0.64

oresc

-0.63

irl

-0.63

-0.61

POSITIVE LOGITS

 Clean

1.35

 Explicit

1.09

Clean

0.98

 cleaner

0.92

clean

0.91

liness

0.80

ergy

0.71

apeake

0.71

-+-+

0.70

 Checks

0.69

Activations Density 0.006%

mentions of terms related to environmental cleanliness and regulatory acts

references to environmental regulations or policies

No Comments

No Known Activations