INDEX

Explanations

phrases representing measurements and quantities

oai_token-act-pair · gpt-3.5-turbo

instances of a specific combination of letters or symbols, possibly indicative of formatting or encoding errors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 sacrific

-0.81

 inform

-0.78

 behavi

-0.68

 Mobil

-0.68

 mediation

-0.66

 behav

-0.66

 fortun

-0.65

 nurture

-0.63

 pestic

-0.63

 obser

-0.63

POSITIVE LOGITS

ï¸ı

1.13

iversary

1.02

lbs

0.94

ths

0.93

âĤ¬

0.91

total

0.91

Â½

0.91

â

0.89

Activations Density 0.182%

phrases representing measurements and quantities

instances of a specific combination of letters or symbols, possibly indicative of formatting or encoding errors

No Comments

No Known Activations