INDEX

Explanations

relevant technical terms and product names

oai_token-act-pair · gpt-3.5-turbo

occurrences of a particular symbol or character in text

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

esses

-0.83

ney

-0.74

glers

-0.72

ugu

-0.70

itionally

-0.70

aret

-0.69

neys

-0.68

amus

-0.67

*/(

-0.67

ulhu

-0.66

POSITIVE LOGITS

Ħ¢

0.84

catentry

0.76

âĦ¢

0.75

peak

0.74

ternity

0.73

tre

0.72

FIELD

0.69

Hart

0.69

ãĤº

0.69

âĢ¢âĢ¢

0.68

Activations Density 0.006%

relevant technical terms and product names

occurrences of a particular symbol or character in text

No Comments

No Known Activations