INDEX

Explanations

the name "Butts"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the suffix "ts"

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

vernment

-0.76

Reviewer

-0.73

 livest

-0.69

[|

-0.66

 slic

-0.66

 suspic

-0.65

 segments

-0.64

ANC

-0.63

inventoryQuantity

-0.62

JPM

-0.62

POSITIVE LOGITS

weet

1.22

hirt

1.15

leeve

1.11

heet

1.04

ween

1.02

ember

1.00

rue

1.00

hower

1.00

onic

0.97

arah

0.96

Activations Density 0.019%

the name "Butts"

occurrences of the suffix "ts"

No Comments

No Known Activations