INDEX

Explanations

phrases indicating preference or choice among options

oai_token-act-pair · gpt-3.5-turbo

comparisons emphasizing alternatives or preferences

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

iola

-0.76

endez

-0.70

eur

-0.70

MG

-0.69

essen

-0.68

isf

-0.67

oops

-0.66

SPA

-0.66

ENE

-0.64

eneg

-0.64

POSITIVE LOGITS

 necessarily

0.93

 relying

0.83

 rely

0.82

 simply

0.80

 anything

0.80

 merely

0.77

 outright

0.76

 perish

0.76

 speculate

0.76

acle

0.74

Activations Density 0.025%

phrases indicating preference or choice among options

comparisons emphasizing alternatives or preferences

No Comments

No Known Activations