INDEX

Explanations

references to specific locations or places

oai_token-act-pair · gpt-3.5-turbo

the word "the" 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 @ 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

thood

-0.81

bg

-0.75

iffe

-0.74

ornings

-0.70

igue

-0.69

aba

-0.69

Ò

-0.68

tumblr

-0.67

acy

-0.67

cheon

-0.67

POSITIVE LOGITS

 slightest

1.42

 latter

1.27

 vast

1.18

 majority

1.16

 greatest

1.12

 biggest

1.11

 strongest

1.08

 heaviest

1.07

 same

1.03

 entire

1.02

Activations Density 0.506%

references to specific locations or places

the word "the" in various contexts

No Comments

No Known Activations