INDEX

Explanations

phrases indicating proximity or closeness

oai_token-act-pair · gpt-3.5-turbo

the preposition "to."

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

 Cosponsors

-0.82

birds

-0.72

 behav

-0.72

 exch

-0.67

PLA

-0.63

Written

-0.63

RF

-0.61

ERG

-0.61

KC

-0.61

 viol

-0.60

POSITIVE LOGITS

sighted

0.89

amaru

0.80

 shore

0.78

shore

0.77

ffee

0.71

 attain

0.70

 schedule

0.69

 reach

0.66

 achieving

0.63

Activations Density 0.063%

phrases indicating proximity or closeness

the preposition "to."

No Comments

No Known Activations