INDEX

Explanations

hashtags related to specific social and political movements or events

oai_token-act-pair · gpt-3.5-turbo

hashtags related to social movements and campaigns

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

 warranties

-0.89

 warranty

-0.71

 reins

-0.71

AFB

-0.64

 leaps

-0.64

 capacities

-0.64

 Petersen

-0.63

=-=-=-=-

-0.61

 exhaustive

-0.60

 Wolfe

-0.60

POSITIVE LOGITS

Fail

0.81

upload

0.80

__

0.79

Must

0.79

_.

0.78

_(

0.78

PP

0.78

Columb

0.78

Brother

0.77

Baby

0.77

Activations Density 0.068%

hashtags related to specific social and political movements or events

hashtags related to social movements and campaigns

No Comments

No Known Activations