INDEX

Explanations

conjunctions, specifically the word "and"

oai_token-act-pair · gpt-3.5-turbo

the conjunction "and" 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

REDACTED

-0.69

panel

-0.69

successfully

-0.69

.*

-0.65

 Â®

-0.64

ential

-0.63

imum

-0.63

reference

-0.62

piring

-0.62

Fed

-0.61

POSITIVE LOGITS

 blah

1.14

 stuff

1.02

 everybody

0.97

romeda

0.97

 yeah

0.95

 maybe

0.94

 hopefully

0.89

 THEN

0.88

 secondly

0.86

 everything

0.83

Activations Density 0.360%

conjunctions, specifically the word "and"

the conjunction "and" in various contexts

No Comments

No Known Activations