INDEX

Explanations

phrases related to accidental events

oai_token-act-pair · gpt-3.5-turbo

instances of the word "accidentally" and its variations

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

nosis

-0.73

riors

-0.73

ciating

-0.70

houses

-0.69

markets

-0.69

raph

-0.69

ETF

-0.68

 conferences

-0.65

tier

-0.65

ophy

-0.64

POSITIVE LOGITS

idental

0.92

 accidentally

0.92

 unintentionally

0.89

 accidental

0.88

 inadvert

0.85

identally

0.85

 unintentional

0.81

 inadvertently

0.80

aneous

0.78

ãĥĻ

0.76

Activations Density 0.025%

phrases related to accidental events

instances of the word "accidentally" and its variations

No Comments

No Known Activations