INDEX

Explanations

positive comments or remarks

oai_token-act-pair · gpt-3.5-turbo

instances of a specific character or symbol repeated throughout the text

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

 vulner

-0.96

 disadvant

-0.89

 mathemat

-0.82

 princ

-0.82

 accomp

-0.76

 constitu

-0.76

 fundament

-0.76

 traged

-0.74

 advis

-0.73

 sacrific

-0.73

POSITIVE LOGITS

ï¸ı

1.12

ï¸

0.92

à¥

0.82

RW

0.81

âĶĢâĶĢ

0.79

ı

0.79

æľ

0.79

\":

0.78

lime

0.77

ãĥ´ãĤ¡

0.75

Activations Density 0.257%

positive comments or remarks

instances of a specific character or symbol repeated throughout the text

No Comments

No Known Activations