INDEX

Explanations

phrases describing correlations or connections between different concepts or variables

oai_token-act-pair · gpt-3.5-turbo

phrases indicating associations or relationships between concepts or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

stall

-0.76

ceans

-0.71

chal

-0.68

thur

-0.67

hene

-0.66

ÄŁ

-0.66

 Trees

-0.64

tein

-0.64

ruary

-0.63

pan

-0.63

POSITIVE LOGITS

ively

0.90

 associations

0.86

 newsp

0.86

 activ

0.84

 associated

0.82

eering

0.80

irect

0.79

vertisements

0.76

unct

0.76

ivity

0.74

Activations Density 0.015%

phrases describing correlations or connections between different concepts or variables

phrases indicating associations or relationships between concepts or conditions

No Comments

No Known Activations