INDEX

Explanations

information related to memory

oai_token-act-pair · gpt-3.5-turbo

references to memory and cognitive processes

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

ppa

-0.76

ulhu

-0.76

ranch

-0.75

phalt

-0.71

ahime

-0.69

wered

-0.68

 Franch

-0.68

udeb

-0.67

WW

-0.67

icans

-0.66

POSITIVE LOGITS

 stimuli

0.99

 cognition

0.85

ceptive

0.85

 cognitive

0.84

 tasks

0.83

 Abilities

0.81

 stimulation

0.80

 Perception

0.78

 impairment

0.77

 behaviors

0.76

Activations Density 0.306%

information related to memory

references to memory and cognitive processes

No Comments

No Known Activations