INDEX

Explanations

phrases related to the term "Tar" in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to "Tar Sands."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

manship

-0.74

swer

-0.72

etimes

-0.65

lihood

-0.63

theless

-0.63

es

-0.62

 lapse

-0.61

sers

-0.60

rontal

-0.59

ALT

-0.59

POSITIVE LOGITS

 sands

1.21

iffs

1.18

zan

1.09

iff

0.99

 Sands

0.90

ried

0.88

onga

0.87

quin

0.87

anium

0.86

pling

0.85

Activations Density 0.034%

phrases related to the term "Tar" in various contexts

references to "Tar Sands."

No Comments

No Known Activations