INDEX

Explanations

sentences where people agree on a certain topic

oai_token-act-pair · gpt-3.5-turbo

phrases indicating consensus or agreement

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

nig

-0.89

Enlarge

-0.68

,)

-0.68

 ILCS

-0.67

)|

-0.66

/+

-0.66

 scratch

-0.65

*)

-0.65

,[

-0.63

\/\/

-0.61

POSITIVE LOGITS

etheless

0.97

ullivan

0.73

onia

0.72

arthed

0.69

 cautiously

0.67

ESCO

0.67

risome

0.66

ufact

0.65

eworks

0.64

osuke

0.62

Activations Density 0.395%

sentences where people agree on a certain topic

phrases indicating consensus or agreement

No Comments

No Known Activations