INDEX

Explanations

scientific terms related to neuroscience and neurobiology

oai_token-act-pair · gpt-3.5-turbo

terms and concepts related to neuroscience and neurobiology

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

gur

-0.85

ISO

-0.82

cake

-0.76

 Strongh

-0.73

 Kinn

-0.71

UTF

-0.71

 Hardcore

-0.70

adra

-0.69

Lago

-0.68

wind

-0.68

POSITIVE LOGITS

 neuroscience

1.12

 biology

1.08

 abnormalities

0.95

 therape

0.93

 Neuroscience

0.93

 physiology

0.92

 neuro

0.89

 neurological

0.89

 therapies

0.89

ochemistry

0.87

Activations Density 0.105%

scientific terms related to neuroscience and neurobiology

terms and concepts related to neuroscience and neurobiology

No Comments

No Known Activations