INDEX

Explanations

relationships between consumption of substances and their health effects

oai_token-act-pair · gpt-3.5-turbo

terms related to consumption and its effects on various factors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

ername

-0.86

PsyNetMessage

-0.80

phia

-0.74

lah

-0.72

appointed

-0.69

boxing

-0.68

usra

-0.67

ittee

-0.67

minus

-0.66

é¾

-0.66

POSITIVE LOGITS

 these

1.19

 certain

1.11

 nont

0.99

non

0.98

 such

0.94

 unconventional

0.92

 specific

0.91

 inexpensive

0.91

 alternative

0.89

 illicit

0.89

Activations Density 0.343%

relationships between consumption of substances and their health effects

terms related to consumption and its effects on various factors

No Comments

No Known Activations