INDEX

Explanations

terms related to mounting or attachment

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "mount" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

rx

-0.79

nesota

-0.77

uel

-0.73

zyme

-0.72

 Quincy

-0.69

ister

-0.69

go

-0.67

Ð¼

-0.67

gone

-0.66

gen

-0.65

POSITIVE LOGITS

mounted

1.05

mount

1.01

aint

0.95

 mount

0.81

 mounted

0.79

ain

0.77

 mounting

0.76

 mounts

0.75

rons

0.74

heny

0.73

Activations Density 0.048%

terms related to mounting or attachment

occurrences of the word "mount" and its variations

No Comments

No Known Activations