INDEX

Explanations

terms related to actions or initiatives happening on a nationwide scale

oai_token-act-pair · gpt-3.5-turbo

terms related to online accessibility and collaboration

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

Americans

-0.94

lees

-0.94

stories

-0.94

Frames

-0.93

bits

-0.91

osaurs

-0.90

Tags

-0.89

tics

-0.89

ernels

-0.88

Nazis

-0.88

POSITIVE LOGITS

 version

1.11

 advisory

0.99

 solution

0.98

 evaluation

0.97

 arrangement

0.96

 suite

0.96

 regimen

0.95

 panel

0.95

 edition

0.95

 batch

0.94

Activations Density 0.386%

terms related to actions or initiatives happening on a nationwide scale

terms related to online accessibility and collaboration

No Comments

No Known Activations