INDEX

Explanations

numbers followed by words related to difficult or negative experiences

oai_token-act-pair · gpt-3.5-turbo

numeric data points, particularly votes or similar numerical values

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

oyd

-0.88

atem

-0.84

ãĤ¡

-0.74

ation

-0.68

ogue

-0.67

Ñĭ

-0.67

 Beckham

-0.66

atives

-0.65

ows

-0.64

omial

-0.64

POSITIVE LOGITS

teenth

0.93

0.90

0.89

0.87

th

0.86

0.85

0.84

0.83

0.82

Activations Density 0.029%

numbers followed by words related to difficult or negative experiences

numeric data points, particularly votes or similar numerical values

No Comments

No Known Activations