INDEX

Explanations

the year 2017

oai_token-act-pair · gpt-3.5-turbo

occurrences of specific years, particularly 2017 and 2018

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

imore

-0.67

cold

-0.64

tub

-0.64

onic

-0.63

 repro

-0.61

 Cold

-0.61

ym

-0.59

hiba

-0.59

inks

-0.59

Bone

-0.58

POSITIVE LOGITS

halla

0.83

alez

0.68

ESV

0.65

 Winners

0.64

umbers

0.63

âĢ²

0.63

Marginal

0.62

rd

0.62

 onwards

0.62

 Remastered

0.62

Activations Density 0.032%

the year 2017

occurrences of specific years, particularly 2017 and 2018

No Comments

No Known Activations