INDEX

Explanations

relationships of blame or responsibility

oai_token-act-pair · gpt-3.5-turbo

phrases related to assigning blame or responsibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

strate

-0.79

vine

-0.78

osphere

-0.77

herer

-0.77

Layer

-0.76

izons

-0.75

Grid

-0.72

nets

-0.71

atories

-0.71

Byte

-0.71

POSITIVE LOGITS

 sins

1.15

 inconvenience

1.05

 crimes

1.04

 sake

0.96

 deaths

0.93

 offences

0.92

 theft

0.92

 absence

0.89

 existence

0.89

 transgress

0.89

Activations Density 0.253%

relationships of blame or responsibility

phrases related to assigning blame or responsibility

No Comments

No Known Activations