INDEX

Explanations

names, specifically the name "Jake" with varying activations

oai_token-act-pair · gpt-3.5-turbo

mentions of individuals named Jake

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

 conduc

-0.79

iary

-0.77

iated

-0.71

amera

-0.68

arily

-0.65

ributed

-0.65

iaries

-0.65

inals

-0.64

 subst

-0.63

 condem

-0.63

POSITIVE LOGITS

glers

1.00

Gy

0.85

 Jake

0.84

unin

0.84

 Skywalker

0.82

ansas

0.80

 McGee

0.79

ango

0.78

warm

0.78

EStream

0.76

Activations Density 0.015%

names, specifically the name "Jake" with varying activations

mentions of individuals named Jake

No Comments

No Known Activations