INDEX

Explanations

phrases related to experiments or trials

oai_token-act-pair · gpt-3.5-turbo

references to experimental conditions or procedures

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

andra

-0.84

HCR

-0.79

olulu

-0.76

atra

-0.73

Words

-0.71

veland

-0.71

ACP

-0.71

cript

-0.70

claimer

-0.68

say

-0.68

POSITIVE LOGITS

imental

1.10

 Experimental

0.81

 experimental

0.79

ists

0.76

 manip

0.75

 laboratory

0.75

 findings

0.75

 experiments

0.74

 explor

0.71

 Prototype

0.70

Activations Density 0.011%

phrases related to experiments or trials

references to experimental conditions or procedures

No Comments

No Known Activations