INDEX

Explanations

specific trigger words like "When"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "When."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

kaya

-0.88

whatever

-0.74

SPONSORED

-0.72

\\\\\\\\

-0.67

oof

-0.67

Í

-0.67

OTHER

-0.66

bart

-0.66

ding

-0.66

aking

-0.66

POSITIVE LOGITS

 asked

1.28

 confronted

1.17

soever

1.10

 pressed

1.05

 faced

1.03

 contacted

0.96

 discussing

0.95

 questioned

0.95

 comparing

0.91

ce

0.89

Activations Density 0.080%

specific trigger words like "When"

occurrences of the word "When."

No Comments

No Known Activations