INDEX

Explanations

mentions of environmental hazards, specifically related to the presence of lead

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 unification

-0.81

ospels

-0.80

 Fellowship

-0.78

joy

-0.75

Kings

-0.75

 Twins

-0.73

 dexter

-0.73

 Marriage

-0.72

UNCH

-0.72

 pivot

-0.71

POSITIVE LOGITS

 contaminants

1.77

 contamin

1.70

 contamination

1.58

 chemicals

1.46

 pollutants

1.45

 toxins

1.44

 ammonia

1.44

 contaminated

1.39

 pollut

1.36

 additives

1.35

Activations Density 0.467%

mentions of environmental hazards, specifically related to the presence of lead

No Comments

No Known Activations