INDEX

Explanations

instances where the word "see" or its variations are used within a sentence

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "we see" and related perceptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

wake

-0.70

 suscept

-0.68

 agric

-0.68

agan

-0.65

 whistle

-0.65

 dispers

-0.63

heid

-0.63

 contrace

-0.63

assisted

-0.62

 reun

-0.61

POSITIVE LOGITS

dust

0.93

awed

0.83

 parallels

0.82

saw

0.77

peak

0.76

eye

0.76

Ĺ

0.74

 visions

0.72

lights

0.72

 similarities

0.70

Activations Density 0.078%

instances where the word "see" or its variations are used within a sentence

instances of the phrase "we see" and related perceptions

No Comments

No Known Activations