INDEX

Explanations

references to successful hits, whether in sports, movies, or conflicts

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "hit" 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 @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

pires

-0.99

etheless

-0.76

otive

-0.68

orld

-0.67

uf

-0.63

pired

-0.62

pite

-0.62

 ILCS

-0.62

cius

-0.61

 subp

-0.61

POSITIVE LOGITS

hit

1.04

hit

0.93

ãĤ¤ãĥĪ

0.86

achi

0.85

OPS

0.80

chens

0.78

Hit

0.77

 hits

0.74

 hitting

0.73

rolet

0.72

Activations Density 0.023%

references to successful hits, whether in sports, movies, or conflicts

occurrences of the word "hit" in various contexts

No Comments

No Known Activations