INDEX

Explanations

words related to difficulties or challenges

oai_token-act-pair · gpt-3.5-turbo

occurrences of the prefix "st"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

isSpecialOrderable

-0.85

deals

-0.73

ource

-0.72

omever

-0.67

ahime

-0.66

 Galile

-0.66

Community

-0.66

meric

-0.65

Buk

-0.65

give

-0.65

POSITIVE LOGITS

st

3.25

St

1.53

st

1.41

ST

1.37

St

1.37

 stalk

1.25

sc

1.20

 sting

1.19

sm

1.18

str

1.18

Activations Density 0.023%

words related to difficulties or challenges

occurrences of the prefix "st"

No Comments

No Known Activations