INDEX

Explanations

mentions of specific groups or organizations

oai_token-act-pair · gpt-3.5-turbo

terms related to organizations and groups, particularly those involved in terrorism or business contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

haar

-0.69

Ô

-0.65

ystem

-0.64

 Assignment

-0.63

alam

-0.62

imon

-0.59

################

-0.59

bernatorial

-0.58

ql

-0.58

%%%%

-0.58

POSITIVE LOGITS

's

1.28

 itself

0.82

ÃŃs

0.74

\'

0.73

 formerly

0.68

maker

0.68

ospace

0.63

bath

0.63

leased

0.62

 annually

0.62

Activations Density 0.403%

mentions of specific groups or organizations

terms related to organizations and groups, particularly those involved in terrorism or business contexts

No Comments

No Known Activations