INDEX

Explanations

words related to the human brain and its functions

oai_token-act-pair · gpt-3.5-turbo

terms associated with cerebral health and insolvency

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

-0.81

busters

-0.71

 Brawl

-0.71

ing

-0.69

rodu

-0.63

-0.62

 Cutter

-0.62

erness

-0.59

 Scully

-0.57

hood

-0.57

POSITIVE LOGITS

pha

0.90

ptions

0.84

spection

0.80

archy

0.78

cemic

0.77

phia

0.76

phony

0.75

ADRA

0.74

geist

0.73

ptive

0.72

Activations Density 0.148%

words related to the human brain and its functions

terms associated with cerebral health and insolvency

No Comments

No Known Activations