INDEX

Explanations

terms related to specific roles or occupations

oai_token-act-pair · gpt-3.5-turbo

terms related to roles and categories within society, particularly in the context of funerals and cultural references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Nutrition

-0.73

 Population

-0.72

 Panther

-0.71

 Potion

-0.70

 Protector

-0.70

 Voting

-0.69

 Surgery

-0.69

 Wedding

-0.68

 Punch

-0.68

Charge

-0.68

POSITIVE LOGITS

acies

1.30

estones

1.15

ancies

1.12

ctions

1.07

itures

1.06

eness

1.05

elines

1.04

atell

1.03

encies

1.03

aton

1.02

Activations Density 0.108%

terms related to specific roles or occupations

terms related to roles and categories within society, particularly in the context of funerals and cultural references

No Comments

No Known Activations