INDEX

Explanations

words related to geographic locations and entities like countries, states, schools, clubs, and organizations

oai_token-act-pair · gpt-3.5-turbo

references to geographical locations, organizations, and competitive entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

racuse

-0.69

abella

-0.69

 roofs

-0.66

croft

-0.62

agnar

-0.62

 chambers

-0.62

usalem

-0.60

peria

-0.60

»Ĵ

-0.59

ories

-0.59

POSITIVE LOGITS

 indeed

0.93

 nonetheless

0.84

 considering

0.80

 compared

0.77

 devoid

0.73

 insofar

0.73

 unto

0.71

 attracting

0.70

 consisting

0.69

 riddled

0.68

Activations Density 0.292%

words related to geographic locations and entities like countries, states, schools, clubs, and organizations

references to geographical locations, organizations, and competitive entities

No Comments

No Known Activations