INDEX

Explanations

words related to geographical locations

oai_token-act-pair · gpt-3.5-turbo

references to cultural or culinary experiences associated with specific regions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ertodd

-0.90

termination

-0.89

 retracted

-0.83

FBI

-0.81

CIA

-0.80

ebin

-0.77

Pwr

-0.75

 Prosecutors

-0.75

DNC

-0.74

DoS

-0.74

POSITIVE LOGITS

 locals

1.17

 tourists

1.17

 cuisine

1.17

 culinary

1.16

 chic

1.16

 tourist

1.14

 quaint

1.14

 Tourism

1.08

 trendy

1.08

 nostalgia

1.07

Activations Density 1.398%

words related to geographical locations

references to cultural or culinary experiences associated with specific regions

No Comments

No Known Activations