INDEX

Explanations

phrases related to caution or warning

oai_token-act-pair · gpt-3.5-turbo

terms related to caution or warnings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

schild

-0.73

eering

-0.65

matically

-0.63

 compact

-0.62

geist

-0.61

 footing

-0.59

tk

-0.58

 onto

-0.57

 heaven

-0.57

 dear

-0.56

POSITIVE LOGITS

ution

1.48

esar

1.44

utions

1.31

ption

1.24

usal

1.13

usa

1.13

UTION

1.08

using

1.05

used

1.04

ust

1.04

Activations Density 0.040%

phrases related to caution or warning

terms related to caution or warnings

No Comments

No Known Activations