INDEX

Explanations

words related to causing a change or reaction in a physical or biological system

oai_token-act-pair · gpt-3.5-turbo

terms related to the concept of induction and its various applications or effects

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

fman

-0.70

dain

-0.70

foundation

-0.69

lain

-0.69

neau

-0.68

 motto

-0.66

esides

-0.65

sonian

-0.64

Ü

-0.64

 Pound

-0.63

POSITIVE LOGITS

 plur

0.95

 induced

0.92

 inducing

0.88

 apopt

0.88

ocy

0.85

 induce

0.84

 induces

0.83

 analges

0.82

orescence

0.82

 hallucinations

0.81

Activations Density 0.027%

words related to causing a change or reaction in a physical or biological system

terms related to the concept of induction and its various applications or effects

No Comments

No Known Activations