INDEX

Explanations

mentions of specific doses or amounts of substances, particularly in relation to medical treatments

oai_token-act-pair · gpt-3.5-turbo

terms related to drug dosages and their effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aldi

-0.79

inates

-0.73

kees

-0.73

beard

-0.70

Pie

-0.69

Pag

-0.67

rade

-0.65

orem

-0.63

pora

-0.61

rimp

-0.61

POSITIVE LOGITS

 dose

1.33

 doses

1.28

 dosage

1.24

 administered

1.10

 regimen

1.09

 intraven

1.04

 orally

1.00

ysis

0.97

 inhal

0.95

 nicotine

0.93

Activations Density 0.088%

mentions of specific doses or amounts of substances, particularly in relation to medical treatments

terms related to drug dosages and their effects

No Comments

No Known Activations