INDEX

Explanations

IP addresses or related terms

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "address" and related terms

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

axis

-0.77

apt

-0.77

aft

-0.74

Bra

-0.69

uj

-0.68

robat

-0.68

rd

-0.68

imposed

-0.67

rub

-0.66

zl

-0.66

POSITIVE LOGITS

 address

0.99

 Address

0.99

 addresses

0.96

address

0.95

Address

0.90

 addr

0.84

holders

0.77

holder

0.74

addr

0.68

idates

0.67

Activations Density 0.016%

IP addresses or related terms

occurrences of the word "address" and related terms

No Comments

No Known Activations