INDEX

Explanations

instances of uncertainty or specific quantities

oai_token-act-pair · gpt-3.5-turbo

references to vague quantifiers indicating a degree of certainty or specificity

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

ults

-0.92

perse

-0.89

 Cosponsors

-0.83

IVERS

-0.82

TeX

-0.80

iddles

-0.79

ULTS

-0.76

enders

-0.76

MSN

-0.75

resses

-0.75

POSITIVE LOGITS

 amount

1.24

 subset

1.11

 percentage

1.00

 degree

0.93

 threshold

0.88

 extent

0.87

 number

0.86

 kind

0.84

 thing

0.82

 portion

0.82

Activations Density 0.029%

instances of uncertainty or specific quantities

references to vague quantifiers indicating a degree of certainty or specificity

No Comments

No Known Activations