INDEX

Explanations

phone numbers or actions related to calling authorities for criminal or emergency situations

oai_token-act-pair · gpt-3.5-turbo

requests for people to provide information by making phone calls

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Flavoring

-0.71

_-

-0.68

 embr

-0.68

inth

-0.67

bilt

-0.66

alde

-0.66

fruit

-0.66

ottest

-0.64

olars

-0.64

izontal

-0.62

POSITIVE LOGITS

1.08

call

0.97

backs

0.95

igraph

0.86

 caller

0.82

 Call

0.81

 Nightmares

0.80

Call

0.79

 attention

0.75

 hotline

0.74

Activations Density 0.054%

phone numbers or actions related to calling authorities for criminal or emergency situations

requests for people to provide information by making phone calls

No Comments

No Known Activations