INDEX

Explanations

words related to focus or concentration

oai_token-act-pair · gpt-3.5-turbo

instances of the word "focus" 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 @ 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

idden

-0.71

added

-0.71

named

-0.67

ania

-0.65

conduct

-0.64

 Britann

-0.62

ston

-0.62

 Gleaming

-0.61

ihad

-0.61

Haunted

-0.60

POSITIVE LOGITS

 focus

0.88

rite

0.84

 focusing

0.82

Focus

0.82

starter

0.80

 focuses

0.80

rals

0.80

focus

0.80

peed

0.77

 Focus

0.77

Activations Density 0.024%

words related to focus or concentration

instances of the word "focus" and its variations

No Comments

No Known Activations