INDEX

Explanations

phrases related to attributing responsibility or blame

oai_token-act-pair · gpt-3.5-turbo

terms related to blame and responsibility, particularly using variations of the word "lay."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

ively

-0.79

qua

-0.67

[+

-0.63

ãĥ¯

-0.63

iles

-0.61

 pandemonium

-0.61

Ther

-0.60

ruciating

-0.59

Enh

-0.59

 Applied

-0.58

POSITIVE LOGITS

 groundwork

1.23

 claim

1.11

 siege

1.01

 bare

1.01

 dormant

0.99

 waste

0.96

 blame

0.87

 foundations

0.82

 down

0.81

ering

0.81

Activations Density 0.037%

phrases related to attributing responsibility or blame

terms related to blame and responsibility, particularly using variations of the word "lay."

No Comments

No Known Activations