INDEX

Explanations

terms related to legal documents and procedures

oai_token-act-pair · gpt-3.5-turbo

references to formal documents or proposals discussing policies and regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

Redd

-0.78

sbm

-0.72

 Scot

-0.69

Chance

-0.67

Sym

-0.66

 Vill

-0.62

é»Ĵ

-0.61

Scot

-0.61

*=-

-0.61

ãĤ¢ãĥ«

-0.60

POSITIVE LOGITS

 itself

1.44

's

0.92

 herself

0.91

 himself

0.81

 finale

0.77

 portion

0.75

wright

0.74

 opener

0.74

 themselves

0.72

keeper

0.72

Activations Density 0.433%

terms related to legal documents and procedures

references to formal documents or proposals discussing policies and regulations

No Comments

No Known Activations