INDEX

Explanations

mentions of the term "Ph" followed by various combinations of letters and numbers

oai_token-act-pair · gpt-3.5-turbo

the abbreviation "Ph" related to academic degrees or professions

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

éĹĺ

-1.10

 fitting

-0.78

PUT

-0.76

âĸ¬âĸ¬

-0.72

fit

-0.70

 Forth

-0.70

*/(

-0.70

æĢ

-0.70

GBT

-0.68

HCR

-0.68

POSITIVE LOGITS

osph

1.41

antom

1.25

oton

1.17

rase

1.12

asing

1.12

ysics

1.10

aser

1.08

ases

1.07

ilipp

1.07

inx

1.06

Activations Density 0.017%

mentions of the term "Ph" followed by various combinations of letters and numbers

the abbreviation "Ph" related to academic degrees or professions

No Comments

No Known Activations