INDEX

Explanations

phrases related to commands or instructions

oai_token-act-pair · gpt-3.5-turbo

repeated special characters indicating emphasized or unusual content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 duplication

-0.64

 decomp

-0.63

 recording

-0.60

gib

-0.58

 fragmentation

-0.57

 recovery

-0.55

 unmarked

-0.55

 stabilization

-0.55

GPS

-0.54

 forwarded

-0.54

POSITIVE LOGITS

£

1.04

Ĵ

0.94

¬

0.93

Ń

0.93

º

0.90

ķ

0.88

¾

0.87

¹

0.86

ı

0.85

½

0.83

Activations Density 0.546%

phrases related to commands or instructions

repeated special characters indicating emphasized or unusual content

No Comments

No Known Activations