INDEX

Explanations

words related to neurotransmitters, such as dopamine, serotonin, GABA, and nicotine

oai_token-act-pair · gpt-3.5-turbo

terms related to neurotransmitters 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 @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

neys

-0.96

earth

-0.90

Earth

-0.90

esan

-0.80

chen

-0.79

 Christy

-0.77

 Galile

-0.75

 Petty

-0.74

fitting

-0.74

ament

-0.74

POSITIVE LOGITS

 injections

1.06

 neurotrans

1.02

phrine

1.00

ergic

1.00

 sulf

0.96

 gluc

0.96

 receptor

0.95

 adrenaline

0.94

 dopamine

0.94

 metabolites

0.94

Activations Density 0.036%

words related to neurotransmitters, such as dopamine, serotonin, GABA, and nicotine

terms related to neurotransmitters and their effects

No Comments

No Known Activations