INDEX

Explanations

words related to technical processes or concepts

oai_token-act-pair · gpt-3.5-turbo

terms related to specific roles, actions, and organizational structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

å§«

-0.63

éĹĺ

-0.59

 Pengu

-0.52

landish

-0.51

 Painter

-0.50

é¾įå

-0.50

emale

-0.50

Georg

-0.50

farious

-0.50

 Moor

-0.48

POSITIVE LOGITS

matically

0.69

 (Â£

0.53

SCP

0.52

ciation

0.52

fully

0.51

lishes

0.50

 Megan

0.50

atu

0.49

lessly

0.49

ams

0.49

Activations Density 0.882%

words related to technical processes or concepts

terms related to specific roles, actions, and organizational structures

No Comments

No Known Activations