INDEX

Explanations

numbers ending in 9 or 10

oai_token-act-pair · gpt-3.5-turbo

references to specific numerical values or scores

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

undai

-0.71

 neighb

-0.68

waves

-0.64

oppy

-0.63

ly

-0.62

leasing

-0.62

reach

-0.61

ibility

-0.61

rir

-0.61

ourses

-0.61

POSITIVE LOGITS

0.96

0.78

OGR

0.77

RD

0.75

ificial

0.72

Â¢

0.72

wine

0.72

 Commando

0.71

 gallons

0.71

Activations Density 0.053%

numbers ending in 9 or 10

references to specific numerical values or scores

No Comments

No Known Activations