INDEX

Explanations

quantitative and mathematical terms within a scientific context

oai_token-act-pair · gpt-3.5-turbo

references to models and modeling 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

azar

-0.81

avorite

-0.72

ulhu

-0.70

emouth

-0.70

olulu

-0.69

entimes

-0.68

odore

-0.66

mare

-0.65

pin

-0.65

omen

-0.64

POSITIVE LOGITS

 organism

0.81

 equations

0.79

model

0.77

models

0.77

 Operator

0.77

LAB

0.75

fitting

0.71

oufl

0.71

 models

0.69

eers

0.67

Activations Density 0.018%

quantitative and mathematical terms within a scientific context

references to models and modeling in various contexts

No Comments

No Known Activations