INDEX

Explanations

legal or official documents containing statements or records

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "affidavit."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

rome

-0.70

oppers

-0.69

OPA

-0.67

tan

-0.66

hy

-0.66

hoff

-0.66

enthal

-0.65

 Nice

-0.65

âĤ¬

-0.64

tics

-0.63

POSITIVE LOGITS

idav

1.14

 affidavit

1.08

 affidav

0.99

 synopsis

0.90

 alleges

0.84

 recount

0.80

 attest

0.79

 warrants

0.75

 documents

0.74

 informant

0.73

Activations Density 0.017%

legal or official documents containing statements or records

occurrences of the word "affidavit."

No Comments

No Known Activations