INDEX

Explanations

terms related to extrapolation and vicarious experiences

oai_token-act-pair · gpt-3.5-turbo

words related to extrapolation and personal experience

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

nces

-0.88

lain

-0.72

itary

-0.71

emate

-0.70

DAQ

-0.69

 Fiorina

-0.67

 Pets

-0.66

ymes

-0.65

erick

-0.64

Mum

-0.64

POSITIVE LOGITS

olated

1.00

 extrap

0.93

olate

0.92

ramid

0.87

orp

0.84

olation

0.80

angled

0.80

ersive

0.76

isode

0.73

ersion

0.73

Activations Density 0.024%

terms related to extrapolation and vicarious experiences

words related to extrapolation and personal experience

No Comments

No Known Activations