INDEX

Explanations

codes, symbols, and specific numbers

oai_token-act-pair · gpt-3.5-turbo

representations of a specific symbol or character

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

ritic

-0.83

entious

-0.82

nces

-0.81

wagen

-0.80

ogie

-0.75

blers

-0.75

rites

-0.74

idy

-0.74

heid

-0.72

earned

-0.72

POSITIVE LOGITS

LAB

0.80

 magnification

0.74

 Expand

0.68

 infinity

0.67

ghai

0.65

Discuss

0.63

_>

0.63

Python

0.62

Emb

0.61

 ÃĹ

0.59

Activations Density 0.017%

codes, symbols, and specific numbers

representations of a specific symbol or character

No Comments

No Known Activations