INDEX

Explanations

dates formatted in different styles

oai_token-act-pair · gpt-3.5-turbo

occurrences of the number 2 in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

awaru

-1.05

 "$:/

-0.70

lehem

-0.68

amaru

-0.67

rolet

-0.67

 stru

-0.67

otle

-0.66

icone

-0.66

olate

-0.64

efully

-0.64

POSITIVE LOGITS

nd

1.44

1.04

1.03

1.02

1.00

0.99

0.98

Activations Density 0.060%

dates formatted in different styles

occurrences of the number 2 in various contexts

No Comments

No Known Activations