INDEX

Explanations

phrases related to authorizing something or giving permission

oai_token-act-pair · gpt-3.5-turbo

special characters or symbols in the text

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

 fishes

-0.75

 welf

-0.71

 dock

-0.70

ãĥ¼ãĥĨãĤ£

-0.66

 ignition

-0.66

 greens

-0.66

 Odin

-0.65

 plaque

-0.64

 antip

-0.63

 charger

-0.63

POSITIVE LOGITS

WHERE

0.97

wait

0.93

they

0.91

yet

0.90

there

0.88

well

0.88

our

0.87

where

0.86

cases

0.85

you

0.84

Activations Density 0.036%

phrases related to authorizing something or giving permission

special characters or symbols in the text

No Comments

No Known Activations