INDEX

Explanations

phrases indicating a desire or intent to do something

oai_token-act-pair · gpt-3.5-turbo

the repeated use of the verb "be" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

PsyNetMessage

-0.71

 fray

-0.69

 suffice

-0.67

iasco

-0.66

pedia

-0.65

 crumble

-0.64

 converge

-0.64

plings

-0.63

strous

-0.63

 spill

-0.63

POSITIVE LOGITS

 able

1.08

friends

0.98

acons

0.88

 honest

0.87

getting

0.87

 thankful

0.87

AUT

0.85

hemoth

0.84

mo

0.81

orc

0.80

Activations Density 0.180%

phrases indicating a desire or intent to do something

the repeated use of the verb "be" in various contexts

No Comments

No Known Activations