INDEX

Explanations

geographical locations or names that could be related to specific areas or organizations

oai_token-act-pair · gpt-3.5-turbo

specific names or terms associated with places, organizations, or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

bleacher

-0.84

bat

-0.81

subject

-0.81

served

-0.79

checks

-0.77

attering

-0.77

uggest

-0.77

rongh

-0.76

add

-0.76

bre

-0.76

POSITIVE LOGITS

 Labs

0.83

 Devices

0.82

senal

0.80

 Vision

0.80

 Productions

0.78

 Partners

0.78

 Networks

0.78

 Investments

0.77

 Industries

0.77

Gas

0.76

Activations Density 0.293%

geographical locations or names that could be related to specific areas or organizations

specific names or terms associated with places, organizations, or entities

No Comments

No Known Activations