INDEX

Explanations

scientific terminology or references

oai_token-act-pair · gpt-3.5-turbo

mentions of "science."

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

 STATES

-0.64

terior

-0.63

oser

-0.62

LOAD

-0.61

theless

-0.61

ESH

-0.61

ription

-0.61

âĢ¢âĢ¢

-0.60

raine

-0.60

leased

-0.60

POSITIVE LOGITS

 Fiction

1.27

 fiction

1.23

craft

0.95

icist

0.91

fiction

0.90

mong

0.83

 literacy

0.80

sonian

0.76

lab

0.76

istries

0.75

Activations Density 0.032%

scientific terminology or references

mentions of "science."

No Comments

No Known Activations