INDEX

Explanations

terms related to cognitive functions or abilities

oai_token-act-pair · gpt-3.5-turbo

words related to cognitive function and mental processes

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

wives

-0.78

wered

-0.75

encer

-0.74

Bey

-0.74

pora

-0.73

olicited

-0.72

enthal

-0.71

Mex

-0.71

encers

-0.70

FORE

-0.70

POSITIVE LOGITS

 disson

1.47

enh

1.16

 impairment

1.12

 behavioural

1.05

 enhancement

1.04

 faculties

0.98

 impair

0.97

 abilities

0.96

 behavi

0.96

 stimulation

0.95

Activations Density 0.028%

terms related to cognitive functions or abilities

words related to cognitive function and mental processes

No Comments

No Known Activations