INDEX

Explanations

mentions of the word "Stone" with varying activations

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Stone."

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

oresc

-0.79

merce

-0.77

olulu

-0.76

ornia

-0.75

orescence

-0.74

ntil

-0.72

unal

-0.70

unct

-0.69

ulate

-0.68

ership

-0.67

POSITIVE LOGITS

falls

0.91

hill

0.88

works

0.83

lings

0.83

 Cold

0.83

ring

0.81

hook

0.81

asure

0.81

asures

0.80

Age

0.79

Activations Density 0.019%

mentions of the word "Stone" with varying activations

instances of the word "Stone."

No Comments

No Known Activations