INDEX

Explanations

references to specific roles or positions held by individuals

oai_token-act-pair · gpt-3.5-turbo

roles and titles related to individuals in various contexts, particularly in the entertainment and professional fields

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

alle

-0.77

omsday

-0.69

lag

-0.69

informed

-0.68

aber

-0.66

irc

-0.66

spir

-0.65

apo

-0.64

anson

-0.63

isson

-0.63

POSITIVE LOGITS

,,

0.86

 extraord

0.84

 Theodore

0.78

 whom

0.78

 Andrew

0.76

 Colin

0.76

 Viktor

0.76

 Stacy

0.74

 Toby

0.73

 Mohammad

0.73

Activations Density 0.224%

references to specific roles or positions held by individuals

roles and titles related to individuals in various contexts, particularly in the entertainment and professional fields

No Comments

No Known Activations