INDEX

Explanations

words related to military operations and defense

oai_token-act-pair · gpt-3.5-turbo

references to "AD" as it relates to various contexts, likely indicating mentions of advertisements or attention-related concepts

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

 Clause

-0.70

 shale

-0.67

 pandemonium

-0.66

 Strip

-0.66

 chlor

-0.63

scr

-0.62

 stopp

-0.62

 tentacles

-0.62

 hydra

-0.62

 stitching

-0.61

POSITIVE LOGITS

AD

4.10

ADS

2.69

ADE

2.11

ads

1.92

ad

1.91

ADA

1.88

AD

1.81

ADD

1.78

ader

1.46

BD

1.41

Activations Density 0.009%

words related to military operations and defense

references to "AD" as it relates to various contexts, likely indicating mentions of advertisements or attention-related concepts

No Comments

No Known Activations