INDEX

Explanations

instances of the word "infinite."

oai_token-act-pair · gpt-3.5-turbo

quantities related to infinity and finiteness

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

bourg

-0.78

crow

-0.74

sburgh

-0.74

Downloadha

-0.73

ington

-0.72

pillar

-0.70

roud

-0.70

Reviewed

-0.69

ribution

-0.69

iard

-0.69

POSITIVE LOGITS

 regress

1.11

 dimensional

0.86

 Tsukuyomi

0.85

urious

0.82

 loops

0.78

inite

0.74

 gratification

0.70

 Loop

0.70

 swaps

0.69

ascript

0.67

Activations Density 0.021%

instances of the word "infinite."

quantities related to infinity and finiteness

No Comments

No Known Activations