INDEX

Explanations

words related to conducting searches or investigations

oai_token-act-pair · gpt-3.5-turbo

instances of the words "search" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

noxious

-0.77

minecraft

-0.76

death

-0.74

ivari

-0.71

cil

-0.70

Downloadha

-0.70

iHUD

-0.69

Production

-0.68

interstitial

-0.68

cigarette

-0.67

POSITIVE LOGITS

 searches

1.00

 searching

0.90

 searched

0.87

 search

0.85

 queries

0.83

 warrant

0.81

 sear

0.79

 frantically

0.78

 warrants

0.75

emouth

0.75

Activations Density 0.022%

words related to conducting searches or investigations

instances of the words "search" and its variations

No Comments

No Known Activations