INDEX

Explanations

keywords related to mounting something physically

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "mount" 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

ister

-0.83

uel

-0.78

glers

-0.75

go

-0.75

nesota

-0.72

rx

-0.72

oru

-0.71

à¦

-0.70

gone

-0.70

 Quincy

-0.70

POSITIVE LOGITS

mounted

1.11

mount

1.03

 mounted

1.02

 mounts

0.97

 mount

0.96

 mounting

0.92

aint

0.87

Mount

0.85

 elevation

0.74

 Mount

0.72

Activations Density 0.017%

keywords related to mounting something physically

occurrences of the word "mount" in various contexts

No Comments

No Known Activations