INDEX

Explanations

personal pronouns followed by verbs or adjectives describing actions or attributes

oai_token-act-pair · gpt-3.5-turbo

pronouns in 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

dp

-0.67

Ĥ¬

-0.67

dding

-0.64

Reply

-0.63

icial

-0.61

inton

-0.59

GCC

-0.59

essions

-0.58

orses

-0.57

POSITIVE LOGITS

 excel

0.78

 thri

0.77

 humble

0.72

 behaves

0.69

 morph

0.68

 popularity

0.68

 thrive

0.68

 creators

0.68

 ubiqu

0.66

 existed

0.66

Activations Density 0.802%

personal pronouns followed by verbs or adjectives describing actions or attributes

pronouns in the text

No Comments

No Known Activations