INDEX

Explanations

the word "vernacular"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "vern" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

FTA

-0.71

raid

-0.69

OHN

-0.67

 regrett

-0.65

FT

-0.62

CHR

-0.60

give

-0.58

Single

-0.57

Wan

-0.57

 horizontal

-0.56

POSITIVE LOGITS

acular

1.37

ormal

0.99

issance

0.91

ocity

0.89

sburg

0.89

ational

0.87

psons

0.86

okes

0.85

itas

0.84

isse

0.83

Activations Density 0.009%

the word "vernacular"

occurrences of the word "vern" in various contexts

No Comments

No Known Activations