INDEX

Explanations

verbs related to causing harm or death to someone

oai_token-act-pair · gpt-3.5-turbo

phrases related to killing or death

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

Verbs related to causing harm or death to someone

Explanation Uploaded by User

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

idth

-0.74

 Nanto

-0.72

":["

-0.65

 Parables

-0.65

CES

-0.63

Balt

-0.63

rouse

-0.60

 emancipation

-0.59

ãĤ¨

-0.58

 Advis

-0.58

POSITIVE LOGITS

 altogether

1.25

 outright

1.12

 prematurely

1.02

 entirely

0.98

 instantly

0.97

 permanently

0.89

 ASAP

0.85

 abruptly

0.85

self

0.84

 alive

0.83

Activations Density 0.289%

verbs related to causing harm or death to someone

phrases related to killing or death

Verbs related to causing harm or death to someone

No Comments

No Known Activations