INDEX

Explanations

words related to sharp objects and actions involving sharpness

oai_token-act-pair · gpt-3.5-turbo

words related to the processes of sharpening and deepening

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

holding

-0.63

TOP

-0.61

 thirds

-0.61

ONE

-0.59

 guidance

-0.59

 Nichols

-0.59

=-=-=-=-=-=-=-=-

-0.58

RNA

-0.57

ORY

-0.57

 Semin

-0.57

POSITIVE LOGITS

ened

1.10

undown

0.99

atche

0.93

inki

0.89

borough

0.86

ening

0.84

rir

0.84

emies

0.83

insula

0.82

ames

0.82

Activations Density 0.016%

words related to sharp objects and actions involving sharpness

words related to the processes of sharpening and deepening

No Comments

No Known Activations