INDEX

Explanations

phrases related to collections or compiling information

oai_token-act-pair · gpt-3.5-turbo

words related to collections or groups

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

¥µ

-0.73

 Archdemon

-0.68

HCR

-0.65

 Concern

-0.64

 Glory

-0.63

IELD

-0.63

Reply

-0.63

 unconditional

-0.62

qua

-0.61

 Thrones

-0.61

POSITIVE LOGITS

oidal

0.98

ider

0.94

ocation

0.92

oqu

0.91

iseum

0.90

ibrary

0.90

ossus

0.85

iery

0.85

ocations

0.85

umin

0.84

Activations Density 0.008%

phrases related to collections or compiling information

words related to collections or groups

No Comments

No Known Activations