INDEX

Explanations

phrases related to unexpected or notable events and outcomes

oai_token-act-pair · gpt-3.5-turbo

phrases that express a lack of expectation or disbelief

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ngth

-0.69

pes

-0.67

 raft

-0.66

ictionary

-0.66

©¶æ

-0.65

 poss

-0.65

 exting

-0.62

oreal

-0.61

 swall

-0.60

rongh

-0.60

POSITIVE LOGITS

 considering

0.78

Reviewer

0.77

 anymore

0.74

 whatsoever

0.69

imaru

0.69

 given

0.68

 Flavoring

0.66

 seeing

0.65

à¤¾

0.64

why

0.64

Activations Density 0.059%

phrases related to unexpected or notable events and outcomes

phrases that express a lack of expectation or disbelief

No Comments

No Known Activations