INDEX

Explanations

terms related to brain stimulation

oai_token-act-pair · gpt-3.5-turbo

terms related to stimulation and its effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Columb

-0.74

©¶æ

-0.69

esan

-0.68

metal

-0.68

 Breaker

-0.65

Cr

-0.64

ãĥĥãĥī

-0.64

 Corsair

-0.63

 Schne

-0.62

arily

-0.62

POSITIVE LOGITS

 stim

1.08

 stimulate

1.00

stim

0.96

 Stim

0.95

aline

0.92

 stimulation

0.91

cffff

0.90

 stimul

0.90

 stimulated

0.89

 stimulating

0.87

Activations Density 0.033%

terms related to brain stimulation

terms related to stimulation and its effects

No Comments

No Known Activations