INDEX

Explanations

words related to cognitive abilities

oai_token-act-pair · gpt-3.5-turbo

terms related to cognitive functions and processes

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

wered

-0.77

pora

-0.77

wives

-0.76

encer

-0.75

govtrack

-0.73

olicited

-0.71

Bey

-0.69

FORE

-0.69

pak

-0.68

enthal

-0.68

POSITIVE LOGITS

 disson

1.48

enh

1.18

 behavioural

1.14

 neuroscience

1.08

 impairment

1.07

 behavioral

1.06

 enhancement

1.01

 abilities

1.00

 behavi

0.99

 deficits

0.97

Activations Density 0.039%

words related to cognitive abilities

terms related to cognitive functions and processes

No Comments

No Known Activations