INDEX

Explanations

words related to categorizing and organizing information

oai_token-act-pair · gpt-3.5-turbo

abbreviations and character names in a narrative context

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ught

-0.84

pton

-0.67

 captivity

-0.63

clone

-0.60

 hindsight

-0.60

ibrary

-0.59

itely

-0.56

 somew

-0.56

veland

-0.55

²¾

-0.55

POSITIVE LOGITS

rob

0.67

rets

0.66

oval

0.65

retched

0.64

iciency

0.61

Õ

0.60

otto

0.60

apor

0.60

oin

0.60

oln

0.59

Activations Density 0.270%

words related to categorizing and organizing information

abbreviations and character names in a narrative context

No Comments

No Known Activations