INDEX

Explanations

mentions of hypothetical situations or possibilities with a focus on specific people or groups and their potential actions or outcomes

oai_token-act-pair · gpt-3.5-turbo

conditional phrases related to expectations or hypothetical outcomes

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ilial

-0.63

indal

-0.59

 externalToEVAOnly

-0.59

sup

-0.57

 Secondly

-0.55

FY

-0.55

 Masquerade

-0.55

 corpor

-0.55

rawdownloadcloneembedreportprint

-0.54

 extends

-0.53

POSITIVE LOGITS

would

1.17

 wouldn

1.10

 would

1.06

 Would

1.01

'd

0.92

Would

0.87

 Wouldn

0.85

 surely

0.80

 probably

0.79

 doubtless

0.79

Activations Density 0.248%

mentions of hypothetical situations or possibilities with a focus on specific people or groups and their potential actions or outcomes

conditional phrases related to expectations or hypothetical outcomes

No Comments

No Known Activations