INDEX

Explanations

words related to recognition and appreciation

oai_token-act-pair · gpt-3.5-turbo

suffixes related to appreciation and valuation

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

TW

-0.69

cro

-0.65

 Harris

-0.62

FW

-0.61

 lapse

-0.59

 hereby

-0.59

 alive

-0.59

CM

-0.58

 felon

-0.57

 spontaneously

-0.57

POSITIVE LOGITS

ated

1.20

ation

1.20

ating

1.17

ations

1.16

ators

1.01

ements

1.00

atory

1.00

ATIONS

0.97

ases

0.97

izations

0.97

Activations Density 0.111%

words related to recognition and appreciation

suffixes related to appreciation and valuation

No Comments

No Known Activations