INDEX

Explanations

words related to a process of making something officially approved or recognized

oai_token-act-pair · gpt-3.5-turbo

terms related to various forms of "ification," indicating processes of transformation or categorization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

©¶æ

-0.72

per

-0.69

bill

-0.67

Pos

-0.64

thritis

-0.64

ker

-0.64

par

-0.62

tiny

-0.62

grass

-0.62

ells

-0.61

POSITIVE LOGITS

ification

1.10

ifications

1.01

yip

0.92

ablishment

0.85

anchester

0.81

IFIC

0.79

enance

0.76

eering

0.76

ations

0.76

ary

0.75

Activations Density 0.012%

words related to a process of making something officially approved or recognized

terms related to various forms of "ification," indicating processes of transformation or categorization

No Comments

No Known Activations