INDEX

Explanations

references to the depth of something, potentially in a figurative or abstract sense

oai_token-act-pair · gpt-3.5-turbo

references to "depth" 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

eer

-0.93

jee

-0.80

abad

-0.77

eers

-0.74

ritten

-0.72

 Sabha

-0.70

rote

-0.70

Bey

-0.70

nee

-0.67

eering

-0.65

POSITIVE LOGITS

 depth

0.96

 Depth

0.88

 penetration

0.85

 perception

0.84

depth

0.77

colour

0.75

cre

0.73

plings

0.71

 depths

0.70

dug

0.68

Activations Density 0.014%

references to the depth of something, potentially in a figurative or abstract sense

references to "depth" in various contexts

No Comments

No Known Activations