INDEX

Explanations

words related to public figures like activists, politicians, athletes, and celebrities

oai_token-act-pair · gpt-3.5-turbo

titles or roles associated with notable individuals, particularly activists and athletes

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ciating

-0.77

âĹ¼

-0.74

fw

-0.74

ascript

-0.73

MpServer

-0.71

inki

-0.70

ibling

-0.70

aber

-0.69

iggle

-0.68

 requisite

-0.68

POSITIVE LOGITS

 extraord

1.15

 Colin

1.05

 Shaun

1.05

 Erik

1.04

 Tony

1.02

 Stefan

1.01

 David

0.99

Ron

0.98

 Sebast

0.98

 Alex

0.97

Activations Density 0.259%

words related to public figures like activists, politicians, athletes, and celebrities

titles or roles associated with notable individuals, particularly activists and athletes

No Comments

No Known Activations