INDEX

Explanations

specific terms and phrases related to locations, organizations, and individuals

oai_token-act-pair · gpt-3.5-turbo

alphanumeric identifiers or names associated with iconic brands or media entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 omission

-0.67

OWS

-0.63

 Trafford

-0.62

DN

-0.61

 disenfranch

-0.60

 Remain

-0.59

 Pages

-0.59

 wolf

-0.58

 Dane

-0.57

#$

-0.56

POSITIVE LOGITS

monary

0.98

irie

0.92

etic

0.88

odic

0.85

incial

0.84

oe

0.84

ilon

0.84

ocry

0.83

perty

0.82

ophe

0.79

Activations Density 0.129%

specific terms and phrases related to locations, organizations, and individuals

alphanumeric identifiers or names associated with iconic brands or media entities

No Comments

No Known Activations