INDEX

Explanations

neural words or terms like "visit" or "visitor"

oai_token-act-pair · gpt-3.5-turbo

words related to visitation or visits to locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

starter

-0.72

 weighing

-0.68

omething

-0.66

 uproar

-0.62

 bare

-0.61

 padding

-0.61

 sprung

-0.61

 releasing

-0.59

 stressing

-0.59

 willpower

-0.59

POSITIVE LOGITS

itors

1.34

itor

1.34

iting

1.09

ibility

1.06

itation

0.95

ison

0.94

ience

0.94

ited

0.94

apore

0.93

its

0.93

Activations Density 0.024%

neural words or terms like "visit" or "visitor"

words related to visitation or visits to locations

No Comments

No Known Activations