INDEX

Explanations

specific occurrences of "if the"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

thood

-0.71

Ò

-0.71

tumblr

-0.68

leeve

-0.67

iffe

-0.65

bg

-0.65

ãĤĭ

-0.62

 Catholicism

-0.61

-0.59

POSITIVE LOGITS

 slightest

1.21

 latter

1.15

 strongest

1.13

 biggest

1.12

 greatest

1.09

 simplest

1.09

 vast

1.06

 easiest

1.04

 largest

1.00

 majority

1.00

Activations Density 1.101%

specific occurrences of "if the"

occurrences of the word "the"

No Comments

No Known Activations