INDEX

Explanations

mental and neurological disorders mentioned in text

oai_token-act-pair · gpt-3.5-turbo

references to various medical or psychological disorders

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

eworld

-0.69

 snipp

-0.67

stanbul

-0.67

uable

-0.64

Sources

-0.64

Pil

-0.64

din

-0.63

vis

-0.63

 Deer

-0.63

raltar

-0.62

POSITIVE LOGITS

 diagnoses

0.93

 disorders

0.89

 disorder

0.86

 Disorders

0.85

 diagnosis

0.85

mania

0.79

ipolar

0.78

otropic

0.78

iac

0.77

 worsen

0.76

Activations Density 0.018%

mental and neurological disorders mentioned in text

references to various medical or psychological disorders

No Comments

No Known Activations