INDEX

Explanations

references to the concept of perception or the act of perceiving

oai_token-act-pair · gpt-3.5-turbo

terms related to perception and how it is shaped by various factors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

istration

-0.73

 Sieg

-0.71

olesterol

-0.68

annis

-0.67

ingen

-0.67

sche

-0.66

loads

-0.66

swick

-0.66

enson

-0.65

acebook

-0.64

POSITIVE LOGITS

 perceptions

0.93

wcsstore

0.78

 perception

0.77

 recoil

0.76

 perceive

0.76

 disson

0.75

ively

0.74

 Perception

0.74

 attractiveness

0.73

FY

0.72

Activations Density 0.032%

references to the concept of perception or the act of perceiving

terms related to perception and how it is shaped by various factors

No Comments

No Known Activations