INDEX

Explanations

words related to specific meanings or interpretations

oai_token-act-pair · gpt-3.5-turbo

words related to the meaning and usage of specific terms

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 experiments

-0.75

 acad

-0.75

 campuses

-0.68

 capacities

-0.67

 faculties

-0.65

 dismantling

-0.65

 seminars

-0.65

 journeys

-0.65

 hemor

-0.64

 inquest

-0.64

POSITIVE LOGITS

âĢİ

0.81

wow

0.77

sama

0.77

Å¡

0.76

beer

0.73

oqu

0.73

foo

0.70

 signifies

0.70

 ______

0.69

love

0.68

Activations Density 0.194%

words related to specific meanings or interpretations

words related to the meaning and usage of specific terms

No Comments

No Known Activations