INDEX

Explanations

phrases related to academic vocabulary

oai_token-act-pair · gpt-3.5-turbo

terms related to vocabulary and linguistic references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 reconciliation

-0.70

 Lilith

-0.70

 Ducks

-0.69

 spotting

-0.68

 Dragonbound

-0.65

 Firefly

-0.62

enstein

-0.61

 Wonderland

-0.61

 Tigers

-0.60

 Lily

-0.59

POSITIVE LOGITS

abulary

1.04

ally

0.98

iferation

0.95

asive

0.92

alf

0.90

ifer

0.89

iculture

0.89

arsity

0.85

Ã¡

0.83

ationally

0.83

Activations Density 0.064%

phrases related to academic vocabulary

terms related to vocabulary and linguistic references

No Comments

No Known Activations