INDEX

Explanations

phrases related to numerical values or statistics

oai_token-act-pair · gpt-3.5-turbo

the word "on" in various contexts, indicating a focus on occurrences or references associated with that term

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

bard

-0.72

########

-0.72

Redd

-0.65

~~~~~~~~

-0.64

usercontent

-0.64

Dispatch

-0.63

loo

-0.63

flies

-0.62

iphate

-0.62

Allah

-0.61

POSITIVE LOGITS

 average

1.27

etime

1.22

 behalf

1.18

shore

1.09

erous

1.05

 steroids

0.83

top

0.83

sets

0.81

site

0.80

 paper

0.79

Activations Density 0.127%

phrases related to numerical values or statistics

the word "on" in various contexts, indicating a focus on occurrences or references associated with that term

No Comments

No Known Activations