INDEX

Explanations

terms related to legal and criminal activities, such as terrorism, charges, and evidence

oai_token-act-pair · gpt-3.5-turbo

concepts related to terrorism and its implications

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hess

-0.74

reach

-0.60

sag

-0.58

 occup

-0.54

rogens

-0.52

main

-0.51

HL

-0.51

 Sinn

-0.51

inding

-0.50

prim

-0.50

POSITIVE LOGITS

etheless

0.91

ï¸ı

0.81

ularity

0.75

IVERS

0.74

Ö¼

0.74

yip

0.72

ancial

0.72

icipated

0.71

Â¯

0.71

apest

0.69

Activations Density 0.284%

terms related to legal and criminal activities, such as terrorism, charges, and evidence

concepts related to terrorism and its implications

No Comments

No Known Activations