INDEX

Explanations

phrases with the structure "self-[word]"

oai_token-act-pair · gpt-3.5-turbo

phrases related to self-identity or self-awareness

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

ulhu

-1.04

 "$:/

-0.83

 Hutch

-0.74

AX

-0.70

 Chains

-0.69

 Rouge

-0.69

 Basin

-0.68

 Shaw

-0.68

 Starr

-0.67

ÙĲ

-0.67

POSITIVE LOGITS

imposed

1.14

proclaimed

1.07

esteem

1.06

talk

1.05

conscious

1.04

destruct

1.04

contained

1.00

decl

0.98

generated

0.98

described

0.96

Activations Density 0.048%

phrases with the structure "self-[word]"

phrases related to self-identity or self-awareness

No Comments

No Known Activations