INDEX

Explanations

numerical values with associated units or measurements

oai_token-act-pair · gpt-3.5-turbo

references to specific dates and numerical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

atis

-0.85

ascus

-0.81

umin

-0.74

 tremend

-0.72

itsch

-0.70

itzer

-0.69

nih

-0.69

etsk

-0.68

edia

-0.67

iqueness

-0.67

POSITIVE LOGITS

th

0.96

arters

0.82

 Minutes

0.80

 minutes

0.79

yrs

0.76

0.75

0.74

0.73

Activations Density 0.047%

numerical values with associated units or measurements

references to specific dates and numerical data

No Comments

No Known Activations