INDEX

Explanations

words related to sorting and organization

oai_token-act-pair · gpt-3.5-turbo

words related to sorting and categorization processes

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

interrupted

-0.89

roach

-0.87

Madison

-0.76

intosh

-0.75

Original

-0.73

peria

-0.72

rises

-0.67

akening

-0.67

ept

-0.67

credit

-0.66

POSITIVE LOGITS

 sorting

0.93

phabet

0.84

 alphabet

0.77

Īè

0.76

ify

0.76

igue

0.75

onom

0.74

 Sort

0.73

 Parenthood

0.72

mates

0.71

Activations Density 0.024%

words related to sorting and organization

words related to sorting and categorization processes

No Comments

No Known Activations