INDEX

Explanations

terms related to non-European immigrants and countries

oai_token-act-pair · gpt-3.5-turbo

terms related to various types of non-state or non-mainstream groups and phenomena

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

CHAT

-0.78

Dialogue

-0.74

wagen

-0.71

AMS

-0.68

adder

-0.68

MAC

-0.66

Hope

-0.65

wark

-0.64

isu

-0.61

instead

-0.61

POSITIVE LOGITS

ensical

0.89

ensable

0.85

theless

0.83

istant

0.78

nor

0.78

ables

0.77

 whatsoever

0.76

 anymore

0.74

existent

0.74

gment

0.72

Activations Density 0.072%

terms related to non-European immigrants and countries

terms related to various types of non-state or non-mainstream groups and phenomena

No Comments

No Known Activations