INDEX

Explanations

terms related to medical conditions and treatments

oai_token-act-pair · gpt-3.5-turbo

terms related to neural activity and chemical interactions within the nervous system

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Grounds

-0.83

 Fool

-0.74

grounds

-0.74

AU

-0.71

 Purg

-0.68

 Pagan

-0.68

 Sins

-0.67

ZZ

-0.66

ruary

-0.66

 Spears

-0.66

POSITIVE LOGITS

emia

1.13

ogenic

1.05

emic

1.04

idine

0.97

oxicity

0.95

oxic

0.94

asis

0.94

ox

0.93

osis

0.93

amine

0.93

Activations Density 0.173%

terms related to medical conditions and treatments

terms related to neural activity and chemical interactions within the nervous system

No Comments

No Known Activations