INDEX

Explanations

phrases or comparisons indicating superiority or similarity in comparison to something else

oai_token-act-pair · gpt-3.5-turbo

phrases that compare two entities or concepts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ô

-0.64

 ende

-0.64

 agre

-0.61

 livest

-0.61

 reperto

-0.61

 accordingly

-0.61

 pestic

-0.60

ertodd

-0.59

 remem

-0.59

phabet

-0.59

POSITIVE LOGITS

 course

1.09

icial

0.84

 sorts

0.81

course

0.76

 ours

0.75

ramer

0.75

tains

0.71

rame

0.64

 ordinary

0.63

mund

0.61

Activations Density 0.083%

phrases or comparisons indicating superiority or similarity in comparison to something else

phrases that compare two entities or concepts

No Comments

No Known Activations