INDEX

Explanations

phrases related to events or occurrences happening once a year

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "annual."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

holes

-0.92

wright

-0.84

UTF

-0.78

agra

-0.74

ymes

-0.72

enes

-0.71

hole

-0.68

 Handler

-0.68

eners

-0.67

enton

-0.67

POSITIVE LOGITS

ized

1.16

ised

0.95

 occurrence

0.92

 pilgr

0.80

ãĥ¼ãĥĨãĤ£

0.79

 appropriation

0.79

 pilgrimage

0.79

ãĥ£

0.77

ivals

0.76

 renewal

0.75

Activations Density 0.033%

phrases related to events or occurrences happening once a year

occurrences of the word "annual."

No Comments

No Known Activations